diff --git a/mlc-chat-config.json b/mlc-chat-config.json new file mode 100644 index 0000000000000000000000000000000000000000..671dd7f0f3594f9f3d8d4b0f90383c83d938d8d5 --- /dev/null +++ b/mlc-chat-config.json @@ -0,0 +1,91 @@ +{ + "version": "0.1.0", + "model_type": "llama", + "quantization": "q4f16_1", + "model_config": { + "hidden_size": 8192, + "intermediate_size": 28672, + "num_attention_heads": 64, + "num_hidden_layers": 80, + "rms_norm_eps": 1e-05, + "vocab_size": 128256, + "tie_word_embeddings": false, + "position_embedding_base": 500000.0, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "context_window_size": 131072, + "prefill_chunk_size": 8192, + "num_key_value_heads": 8, + "head_dim": 128, + "tensor_parallel_shards": 1, + "pipeline_parallel_stages": 1, + "max_batch_size": 128 + }, + "vocab_size": 128256, + "context_window_size": 131072, + "sliding_window_size": -1, + "prefill_chunk_size": 8192, + "attention_sink_size": -1, + "tensor_parallel_shards": 1, + "pipeline_parallel_stages": 1, + "temperature": 0.6, + "presence_penalty": 0.0, + "frequency_penalty": 0.0, + "repetition_penalty": 1.0, + "top_p": 0.9, + "tokenizer_files": [ + "tokenizer.json", + "tokenizer_config.json" + ], + "tokenizer_info": { + "token_postproc_method": "byte_level", + "prepend_space_in_encode": false, + "strip_space_in_decode": false + }, + "conv_template": { + "name": "llama-3", + "system_template": "<|start_header_id|>system<|end_header_id|>\n\n{system_message}<|eot_id|>", + "system_message": "You are a helpful, respectful and honest assistant.", + "system_prefix_token_ids": [ + 128000 + ], + "add_role_after_system_message": true, + "roles": { + "user": "<|start_header_id|>user", + "assistant": "<|start_header_id|>assistant" + }, + "role_templates": { + "user": "{user_message}", + "assistant": "{assistant_message}", + "tool": "{tool_message}" + }, + "messages": [], + "seps": [ + "<|eot_id|>" + ], + "role_content_sep": "<|end_header_id|>\n\n", + "role_empty_sep": "<|end_header_id|>\n\n", + "stop_str": [ + "<|end_of_text|>", + "<|eot_id|>" + ], + "stop_token_ids": [ + 128001, + 128009 + ], + "function_string": "", + "use_function_calling": false + }, + "pad_token_id": 0, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ] +} \ No newline at end of file diff --git a/ndarray-cache.json b/ndarray-cache.json new file mode 100644 index 0000000000000000000000000000000000000000..420b23696f3aab979c26be5d9ec7030452650be5 --- /dev/null +++ b/ndarray-cache.json @@ -0,0 +1,12559 @@ +{ + "metadata": { + "ParamSize": 805, + "ParamBytes": 39688355840.0, + "BitsPerParam": 4.356224340918386 + }, + "records": [ + { + "dataPath": "params_shard_0.bin", + "format": "raw-shard", + "nbytes": 525336576, + "records": [ + { + "name": "lm_head.q_weight", + "shape": [ + 128256, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 525336576, + "byteOffset": 0 + } + ], + "md5sum": "478ba82a33942a6ad70ee42e8fb9c629" + }, + { + "dataPath": "params_shard_1.bin", + "format": "raw-shard", + "nbytes": 65667072, + "records": [ + { + "name": "lm_head.q_scale", + "shape": [ + 128256, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 65667072, + "byteOffset": 0 + } + ], + "md5sum": "fdc92413dd29e9ba807757e02d8d7824" + }, + { + "dataPath": "params_shard_2.bin", + "format": "raw-shard", + "nbytes": 525336576, + "records": [ + { + "name": "model.embed_tokens.q_weight", + "shape": [ + 128256, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 525336576, + "byteOffset": 0 + } + ], + "md5sum": "14bd89a96e685b4aabec3b21d76475a5" + }, + { + "dataPath": "params_shard_3.bin", + "format": "raw-shard", + "nbytes": 65667072, + "records": [ + { + "name": "model.embed_tokens.q_scale", + "shape": [ + 128256, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 65667072, + "byteOffset": 0 + } + ], + "md5sum": "fca0f406a72aa344dbce3b9c2ebf3597" + }, + { + "dataPath": "params_shard_4.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.0.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "1f48b4c026132d289dda1518e385d475" + }, + { + "dataPath": "params_shard_5.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "5224118d911b8bc6482c000474f9dd34" + }, + { + "dataPath": "params_shard_6.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.0.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "2fabd7dc21444e43d875e46d368ab284" + }, + { + "dataPath": "params_shard_7.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.0.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a2fa07db651eb4527680402f54c35192" + }, + { + "dataPath": "params_shard_8.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.0.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5e589c315ff8cf378226911332cde954" + }, + { + "dataPath": "params_shard_9.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "3a179d63a580c6234be7f930c040d24d" + }, + { + "dataPath": "params_shard_10.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.1.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "8ef433592faf835c94eaa639d2fbb401" + }, + { + "dataPath": "params_shard_11.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.1.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e58ca887e31e80723b84f3e8eea6a893" + }, + { + "dataPath": "params_shard_12.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "aeb94046282fb99efdf1a0a86678e6d6" + }, + { + "dataPath": "params_shard_13.bin", + "format": "raw-shard", + "nbytes": 29392896, + "records": [ + { + "name": "model.layers.0.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 0 + }, + { + "name": "model.layers.0.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 16384 + }, + { + "name": "model.layers.0.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14696448 + }, + { + "name": "model.layers.0.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14712832 + }, + { + "name": "model.layers.0.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19955712 + }, + { + "name": "model.layers.1.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24150016 + } + ], + "md5sum": "eb9aa591d9706115ed672503aae547bf" + }, + { + "dataPath": "params_shard_14.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.1.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "8f43cb831b4fd83b1e54f1c9abf8680f" + }, + { + "dataPath": "params_shard_15.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "97002b06e36e47f4af1a64676ec6c781" + }, + { + "dataPath": "params_shard_16.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.1.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.1.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.1.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.1.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.2.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "fe1d431860c523bdac07bfbac5d72607" + }, + { + "dataPath": "params_shard_17.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "a02df41118992fd83ac47cb2adec04ba" + }, + { + "dataPath": "params_shard_18.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.2.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "80cf21ce3db14cd87602628b118f31d2" + }, + { + "dataPath": "params_shard_19.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.2.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a01c9b9222f0f99890a31d2964ecf003" + }, + { + "dataPath": "params_shard_20.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.2.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c6341815445711578cad2475bd3281a2" + }, + { + "dataPath": "params_shard_21.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "bf5f6a2762534babaee6002b7c5e4981" + }, + { + "dataPath": "params_shard_22.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.2.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.2.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.2.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.2.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.3.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "c639518ef7ca591dd0ad5482c80cb1f1" + }, + { + "dataPath": "params_shard_23.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "577798cfea1a00f9f90b103d3f77ad70" + }, + { + "dataPath": "params_shard_24.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.3.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "00ff10fa5488eb8737c8ff27c67f5078" + }, + { + "dataPath": "params_shard_25.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.3.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b3ea51ac7cc4c2d4cd081923e0618cf2" + }, + { + "dataPath": "params_shard_26.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.3.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a3b86cb4943ceb97ceafbc83c9025db8" + }, + { + "dataPath": "params_shard_27.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.4.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "467aabb5a45fc2135ecfef2baf1304ce" + }, + { + "dataPath": "params_shard_28.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.4.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "0f97f40e96863ceb764b8b860aff4ffc" + }, + { + "dataPath": "params_shard_29.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.3.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.3.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.3.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.3.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.4.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "460180eb0088df354c6109933e6d0a8f" + }, + { + "dataPath": "params_shard_30.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.10.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b4690d8d5e7a206f1e96e08e49966089" + }, + { + "dataPath": "params_shard_31.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "7263c2a92bc62523b2a1d96b0f94ae71" + }, + { + "dataPath": "params_shard_32.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.10.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "9a0cd0488c3f84ea7dd8efc3273342e1" + }, + { + "dataPath": "params_shard_33.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.10.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "96f57971d96f44daf00ac6d28235cc81" + }, + { + "dataPath": "params_shard_34.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.10.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ecf40a0d2842251461b9ef16b456a4dd" + }, + { + "dataPath": "params_shard_35.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "745ae47f86b58838da914a852359da1d" + }, + { + "dataPath": "params_shard_36.bin", + "format": "raw-shard", + "nbytes": 28360704, + "records": [ + { + "name": "model.layers.4.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.10.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.10.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.10.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.10.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 18907136 + }, + { + "name": "model.layers.10.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 24150016 + }, + { + "name": "model.layers.11.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 28344320 + } + ], + "md5sum": "07745b2b534bae526a48474e7f953b18" + }, + { + "dataPath": "params_shard_37.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "bb8a9b88b6be437ba344256f61031e1c" + }, + { + "dataPath": "params_shard_38.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.11.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "c196ef174d2371e3d69aed5407d332e1" + }, + { + "dataPath": "params_shard_39.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.11.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "cf8cde1d3cff64cfbe72f8d09c28076d" + }, + { + "dataPath": "params_shard_40.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.11.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "36930f3d76ef0887208e5e1015f88e44" + }, + { + "dataPath": "params_shard_41.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "1af4805c4447d2ec8eba696fe25c52b2" + }, + { + "dataPath": "params_shard_42.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.12.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "8869c29a47950cb27e7c9fa8fb794d87" + }, + { + "dataPath": "params_shard_43.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.12.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5956065ad61026f52eddac92bfc47da1" + }, + { + "dataPath": "params_shard_44.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f2357110a8c7e822388d5a342bcdd688" + }, + { + "dataPath": "params_shard_45.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.11.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.11.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.11.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.11.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.12.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "3f90a03f78a476df37688f9c1d8edd3c" + }, + { + "dataPath": "params_shard_46.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.12.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "862e2b318a696a047df4cb9943540982" + }, + { + "dataPath": "params_shard_47.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "0c9708d4d3beb021c6e719d67012d3eb" + }, + { + "dataPath": "params_shard_48.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.12.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.12.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.12.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.12.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.13.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "66046cae8850f9cee23128dfa81f9f78" + }, + { + "dataPath": "params_shard_49.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b4b14e208667a21560bdcd87973f12cd" + }, + { + "dataPath": "params_shard_50.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.13.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "da0e2b46da0aaaf95786371416056073" + }, + { + "dataPath": "params_shard_51.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.13.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9efc3a2d650fdb72eacfcbe48a3728f5" + }, + { + "dataPath": "params_shard_52.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.13.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5669f71839830937bb3116d7fb539be0" + }, + { + "dataPath": "params_shard_53.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "17e91c624b5d27d4e74d19cc1aeb9d6b" + }, + { + "dataPath": "params_shard_54.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.13.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.13.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.13.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.13.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.14.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "cd0316639593590bf8da5ad779061944" + }, + { + "dataPath": "params_shard_55.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "6a0fd8ef49748614f5abaad65fd5403e" + }, + { + "dataPath": "params_shard_56.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.14.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "2df32e1b0e9d9d55c7fb2be6071d2ec6" + }, + { + "dataPath": "params_shard_57.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.14.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1ab54fb942c2d1061348be00699cf432" + }, + { + "dataPath": "params_shard_58.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.14.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b06c9d90234e921fef0be15e51b8f84b" + }, + { + "dataPath": "params_shard_59.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "209968c960c478c17c36bc5a116e18bb" + }, + { + "dataPath": "params_shard_60.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.15.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "e5bd4cba4bbfe61ae61c777e01bd416e" + }, + { + "dataPath": "params_shard_61.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.15.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "701b92f89e57b90e3b00a06699d61ed3" + }, + { + "dataPath": "params_shard_62.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.15.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "692e3e23352560608aabf14eca204eec" + }, + { + "dataPath": "params_shard_63.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.14.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.14.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.14.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.14.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.15.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "f5219ddef7280c0f3eee52164cbcbd7e" + }, + { + "dataPath": "params_shard_64.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.15.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "9ff444fdb579464b03dce77fd1df49c9" + }, + { + "dataPath": "params_shard_65.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a79810deb4ab08d89ec7c16fd103e1b1" + }, + { + "dataPath": "params_shard_66.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.15.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.15.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.15.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.15.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.16.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "8a981e51209b3b66837faf8d48a11c68" + }, + { + "dataPath": "params_shard_67.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "9eeabfcda2274eee752aead92e01a716" + }, + { + "dataPath": "params_shard_68.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.16.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "67600ff69f4e75c4ea18befa2452c6a8" + }, + { + "dataPath": "params_shard_69.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.16.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e251ed888cd588b16a795833f4726986" + }, + { + "dataPath": "params_shard_70.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.16.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "00a5871757c8e1f6133750b60b68f1de" + }, + { + "dataPath": "params_shard_71.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "1d23f2fb33a622cab2f3251e2be21f48" + }, + { + "dataPath": "params_shard_72.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.16.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.16.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.16.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.16.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.17.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "e43243cb26a563649d1996eeeb39348f" + }, + { + "dataPath": "params_shard_73.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c6afb8a967cf418afeead1c7e152ff24" + }, + { + "dataPath": "params_shard_74.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.17.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "3a76cce2864e928484474e1d9d5e7705" + }, + { + "dataPath": "params_shard_75.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.17.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "058550cb7c768be0040146db7e2e59b5" + }, + { + "dataPath": "params_shard_76.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.17.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d8ae58f3c1f6d010714533d8381cfe13" + }, + { + "dataPath": "params_shard_77.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.18.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "de2371aba3377cb1811181371bb29f0f" + }, + { + "dataPath": "params_shard_78.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6b8d47b154a4bf3b07ec12e51256519a" + }, + { + "dataPath": "params_shard_79.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.17.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.17.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.17.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.17.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.18.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "c5257f5fc17674b340105889512905e8" + }, + { + "dataPath": "params_shard_80.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.18.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "4eeb1d95e7876be7079f6469f475fbe8" + }, + { + "dataPath": "params_shard_81.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "3ec5269e628312924a53235bf6e6f0b6" + }, + { + "dataPath": "params_shard_82.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.18.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "4a34f21a1073405749dc1a2534309c26" + }, + { + "dataPath": "params_shard_83.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "7a08b3be9c3b6d575b9ff371d341532f" + }, + { + "dataPath": "params_shard_84.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.18.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.18.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.18.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.18.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.19.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "1e0706c47185aa705ddb31503617105a" + }, + { + "dataPath": "params_shard_85.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "ae2a599c2ef43422300713746586d7b1" + }, + { + "dataPath": "params_shard_86.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.19.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "3b2a4c5af5b17aea14b347f0731988fb" + }, + { + "dataPath": "params_shard_87.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.19.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "08da37471a2438f23db68ad67d572de1" + }, + { + "dataPath": "params_shard_88.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.19.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4bf8cb6a6a29f468d9dce35c3ef30e4f" + }, + { + "dataPath": "params_shard_89.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "41fa9674cca17690c288a833ce8b825e" + }, + { + "dataPath": "params_shard_90.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.19.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.19.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.19.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.19.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.20.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "deb99267bf3931128a2b88533e0a790e" + }, + { + "dataPath": "params_shard_91.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "116849d108445e9887bdb4e932230f10" + }, + { + "dataPath": "params_shard_92.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.20.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "8bbce71b27c8da54681505d3993176f1" + }, + { + "dataPath": "params_shard_93.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.20.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "aac2ae28c05cb864db7258354689f887" + }, + { + "dataPath": "params_shard_94.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.20.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6f05bbf0e7fa9f6b2dfbf9a2f454c355" + }, + { + "dataPath": "params_shard_95.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.21.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "34fa003c2e52823df6fdc20282873243" + }, + { + "dataPath": "params_shard_96.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "be7bf1030ebe701051d0a14d23230884" + }, + { + "dataPath": "params_shard_97.bin", + "format": "raw-shard", + "nbytes": 29392896, + "records": [ + { + "name": "model.layers.20.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.20.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.20.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.20.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.21.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + }, + { + "name": "model.layers.21.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 29376512 + } + ], + "md5sum": "84efe5577413aa2e74b8728d47ca487b" + }, + { + "dataPath": "params_shard_98.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "083808f910f5df2f51a9ccbf7b3950a2" + }, + { + "dataPath": "params_shard_99.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.21.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "dd57959c731aec9b10e0150f062168e9" + }, + { + "dataPath": "params_shard_100.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.21.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3483649d0278247c6364bdfbdc05136f" + }, + { + "dataPath": "params_shard_101.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "722401240f773a477b4662b94327bf8a" + }, + { + "dataPath": "params_shard_102.bin", + "format": "raw-shard", + "nbytes": 18907136, + "records": [ + { + "name": "model.layers.21.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.21.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.21.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 14696448 + }, + { + "name": "model.layers.22.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + } + ], + "md5sum": "f0d3289d1b50d3c0cd03a959ccd49bac" + }, + { + "dataPath": "params_shard_103.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0a4a717564d9978b88f9eeaed48d10b8" + }, + { + "dataPath": "params_shard_104.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.22.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "3d72b4760c003bfa012f10c864831b67" + }, + { + "dataPath": "params_shard_105.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.22.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1fb9e2d10b3b5dfc7ccbc0a407819552" + }, + { + "dataPath": "params_shard_106.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.22.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "748db9556faf802a37b69e1f00201a48" + }, + { + "dataPath": "params_shard_107.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "00f6750954313babf42cc254c94ec178" + }, + { + "dataPath": "params_shard_108.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.22.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.22.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.22.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.22.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.23.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "58012bbd0fae88d70f40007380dbbde2" + }, + { + "dataPath": "params_shard_109.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "5b8e93f9b197b75fb21818558afa2951" + }, + { + "dataPath": "params_shard_110.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.23.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "4ebc7608cc606a063933d0e58925674e" + }, + { + "dataPath": "params_shard_111.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.23.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "ca90be5708f52b68042cd42e6e24d763" + }, + { + "dataPath": "params_shard_112.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.23.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1cd75eaecf9a1ec3c9d05f7d2898b09d" + }, + { + "dataPath": "params_shard_113.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "dbb4fea35571613101cecc37342f706a" + }, + { + "dataPath": "params_shard_114.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.23.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.23.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.23.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.23.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.24.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "2993ae77d8a6622ad515601f02a6b967" + }, + { + "dataPath": "params_shard_115.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "1fc50351a5dd4c5a4e0e8cc4cf8054f3" + }, + { + "dataPath": "params_shard_116.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.24.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "b6d09f7755c46f3d68153053fe17aedd" + }, + { + "dataPath": "params_shard_117.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.24.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "09e52d5e57461eae9a94ca041a3141e7" + }, + { + "dataPath": "params_shard_118.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.24.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "8faeb8e35ee614dcc5adf77fed2467e7" + }, + { + "dataPath": "params_shard_119.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6e91f57f93982a48abafef05fdde5eca" + }, + { + "dataPath": "params_shard_120.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.24.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.24.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.24.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.24.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.25.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "7dda1d62f2cdca5f9a8102cd4031dafb" + }, + { + "dataPath": "params_shard_121.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "120aaba75daf75f982aa3f136fd1a598" + }, + { + "dataPath": "params_shard_122.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.25.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "4bd92b8efb91e0bc0725e28d4b83d9ef" + }, + { + "dataPath": "params_shard_123.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.25.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e1753ddfbef5950ddb6e17971da0b0af" + }, + { + "dataPath": "params_shard_124.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.25.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "2434d3e81579621e430c4b7bbcb6480b" + }, + { + "dataPath": "params_shard_125.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "fcce5c1068fce23a481293507387a980" + }, + { + "dataPath": "params_shard_126.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.26.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "64c6fc29e0fad1684a65712f4b0d6db9" + }, + { + "dataPath": "params_shard_127.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.26.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8e4ebb49b29b9ff16e6024451a902894" + }, + { + "dataPath": "params_shard_128.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.26.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ecceb1fd6e2f4447c4350d7dc9d14f1a" + }, + { + "dataPath": "params_shard_129.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.25.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.25.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.25.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.25.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.26.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "f8277fbce41ee7af978bf1c973d06322" + }, + { + "dataPath": "params_shard_130.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.26.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a0d99b1621929238714d41691a46a532" + }, + { + "dataPath": "params_shard_131.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "073b39f943891f8bc851603fd91d126b" + }, + { + "dataPath": "params_shard_132.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.26.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.26.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.26.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.26.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.27.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "7ec27f47783851356998104b6a01e340" + }, + { + "dataPath": "params_shard_133.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "018964ce2d8d72daf38270a2b196b797" + }, + { + "dataPath": "params_shard_134.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.27.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "7761941db68e68c5b8b4a2c3cdd008e9" + }, + { + "dataPath": "params_shard_135.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.27.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "9da1f8434f1cd234adf4047096397362" + }, + { + "dataPath": "params_shard_136.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.27.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "67c535f9dad12a21af6954387583266b" + }, + { + "dataPath": "params_shard_137.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "418d04b1c4c5db1e2d0cd0c29bda3b87" + }, + { + "dataPath": "params_shard_138.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.27.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.27.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.27.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.27.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.28.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "914f3f783475b4695656ed18e6069235" + }, + { + "dataPath": "params_shard_139.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f00a4fce536888643895d48e5a0c0fbb" + }, + { + "dataPath": "params_shard_140.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.28.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "7288af9c13c140ceb25789b5001077ec" + }, + { + "dataPath": "params_shard_141.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.28.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "17ba4bb3e604ed455b21faa051457f3c" + }, + { + "dataPath": "params_shard_142.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.28.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "fd2e8a2006e565a6cb220c2405495eef" + }, + { + "dataPath": "params_shard_143.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "53eb960630e0dc1783b6783b02b332bb" + }, + { + "dataPath": "params_shard_144.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.29.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "99f9460797bf14f92e6cd2b01715be51" + }, + { + "dataPath": "params_shard_145.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.29.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "280dcc7693590a9bce0abb23b228ec51" + }, + { + "dataPath": "params_shard_146.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.29.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5df26b669d0ca925795bd2bb12d11631" + }, + { + "dataPath": "params_shard_147.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.28.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.28.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.28.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.28.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.29.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "47c848c4488aaf043ae0689ce4127c78" + }, + { + "dataPath": "params_shard_148.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.29.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f441f3bd9a118c05af100f918fbbe759" + }, + { + "dataPath": "params_shard_149.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6a864f1c69ef569a223a618efd98ab59" + }, + { + "dataPath": "params_shard_150.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.29.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.29.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.29.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.29.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.30.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "9e117804b10e128350302f76e57f4631" + }, + { + "dataPath": "params_shard_151.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "581c772bf4ad5b694de9352bee48f583" + }, + { + "dataPath": "params_shard_152.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.30.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "596633508b23d18a418d651019d4e574" + }, + { + "dataPath": "params_shard_153.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.30.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a90f4c7c66cd170489f4576419d70eb6" + }, + { + "dataPath": "params_shard_154.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.30.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "9b56a5bcacd0654a02e040171110f0d0" + }, + { + "dataPath": "params_shard_155.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ab160f62321d79144abb97ccbd6d19d4" + }, + { + "dataPath": "params_shard_156.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.30.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.30.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.30.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.30.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.31.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "9528c225c802fc369a63f337e3737fc0" + }, + { + "dataPath": "params_shard_157.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "dd91d56435dbefcffdb3fda44293d0ff" + }, + { + "dataPath": "params_shard_158.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.31.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "09568a58ce81bc58605f6735f5c4fd4c" + }, + { + "dataPath": "params_shard_159.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.31.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "58d3690700adbef510c70506c7aeef87" + }, + { + "dataPath": "params_shard_160.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.31.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5be50d69aed72efa056a7f27de061624" + }, + { + "dataPath": "params_shard_161.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.32.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "7c49df8eb17af716f959369c665b2dff" + }, + { + "dataPath": "params_shard_162.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.32.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c50045a98ebb445351e5a71f561235bd" + }, + { + "dataPath": "params_shard_163.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.31.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.31.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.31.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.31.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.32.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "a9d9f495a77a1ca182ecacefd50fcaaa" + }, + { + "dataPath": "params_shard_164.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.32.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a38d1bb0d1812291e7d541bf5959901f" + }, + { + "dataPath": "params_shard_165.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "19c8a79ab49dcc781a822a4295cb0b13" + }, + { + "dataPath": "params_shard_166.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.32.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "d23ce4c75c279507bd4ce7cc6895a5c4" + }, + { + "dataPath": "params_shard_167.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2a46ac5914e75ba14dd595bf7e5db1ef" + }, + { + "dataPath": "params_shard_168.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.32.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.32.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.32.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.32.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.33.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "2dcfcef4214d595c04dac830502878f9" + }, + { + "dataPath": "params_shard_169.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "86c4243cd19ce8a46df49c44f19868b5" + }, + { + "dataPath": "params_shard_170.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.33.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "e86186f308c443a164551d0963442f8e" + }, + { + "dataPath": "params_shard_171.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.33.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "bd0915dce7f4bd96331592a5c2ce25fe" + }, + { + "dataPath": "params_shard_172.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.33.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "1d216cc9b2bef9a3fc4af875de1c98e8" + }, + { + "dataPath": "params_shard_173.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f3274dbb567c77015ef419b97de4fa2b" + }, + { + "dataPath": "params_shard_174.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.33.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.33.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.33.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.33.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.34.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "6d4d42159971b1c6a06401a701fe835d" + }, + { + "dataPath": "params_shard_175.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "a570722e9d7f43a0d31f6153fac4cb55" + }, + { + "dataPath": "params_shard_176.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.34.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "e784a31bb7ee3734a8cbf447ab09d236" + }, + { + "dataPath": "params_shard_177.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.34.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "563c9a7c6487d123575166a3a229b77c" + }, + { + "dataPath": "params_shard_178.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.34.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "657c2f606f43f1ccd350756a8da72626" + }, + { + "dataPath": "params_shard_179.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.35.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "6b4b7d4786f7be91fcfbe9c1b563d538" + }, + { + "dataPath": "params_shard_180.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "689d594ea65cc6cdac62aa99efcd8b30" + }, + { + "dataPath": "params_shard_181.bin", + "format": "raw-shard", + "nbytes": 29392896, + "records": [ + { + "name": "model.layers.34.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.34.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.34.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.34.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.35.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + }, + { + "name": "model.layers.35.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 29376512 + } + ], + "md5sum": "acc2a964752b4c7c1acb6fbc0af38fc8" + }, + { + "dataPath": "params_shard_182.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "86a0ab3a203f278c8512084d2cf95ec7" + }, + { + "dataPath": "params_shard_183.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.35.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "3d61712b027e639bf5a383202d289cde" + }, + { + "dataPath": "params_shard_184.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.35.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3c48bbbe765c244da5133866fe1bdf50" + }, + { + "dataPath": "params_shard_185.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2eda07cc79b1e65873040ba41aff947d" + }, + { + "dataPath": "params_shard_186.bin", + "format": "raw-shard", + "nbytes": 18907136, + "records": [ + { + "name": "model.layers.35.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.35.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.35.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 14696448 + }, + { + "name": "model.layers.36.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + } + ], + "md5sum": "225bb284b21c6d8e958803a3ef1080f6" + }, + { + "dataPath": "params_shard_187.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "5cbf7704a5eef88fac4ceb12090c4892" + }, + { + "dataPath": "params_shard_188.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.36.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "b6a195eb2a81ac53d328005f8b54c056" + }, + { + "dataPath": "params_shard_189.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.36.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "597bb32af314086c1e138f1e30c86e62" + }, + { + "dataPath": "params_shard_190.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.36.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "8a5c28a16fa43e3cdb059180ea9289b6" + }, + { + "dataPath": "params_shard_191.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.37.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "97b0940dbef5bd00ef3b21cc2e81a591" + }, + { + "dataPath": "params_shard_192.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.36.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.36.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.36.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.36.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.37.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "aa159e85e0f32f3019949d19b923c0f5" + }, + { + "dataPath": "params_shard_193.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "c3f1b0c9fb150df382c4ed2a679129d2" + }, + { + "dataPath": "params_shard_194.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.37.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "705af047f4bced5ca86a44a6e83b9619" + }, + { + "dataPath": "params_shard_195.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.37.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "efc151050c1abc8b8997f863508b1f74" + }, + { + "dataPath": "params_shard_196.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.37.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "803c497035d5e93aa5b347712beec4c8" + }, + { + "dataPath": "params_shard_197.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6453d895e12e1d79903fe023a78769af" + }, + { + "dataPath": "params_shard_198.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.37.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.37.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.37.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.37.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.38.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "078cae7aac20ace78b64ae9aed562aec" + }, + { + "dataPath": "params_shard_199.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "43fd8889a2ec304b2c040fdbed216067" + }, + { + "dataPath": "params_shard_200.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.38.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "aec41f866e71f2f587740a4c10484e6b" + }, + { + "dataPath": "params_shard_201.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.38.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5850ab4b5cc4944acc7546c343d834e7" + }, + { + "dataPath": "params_shard_202.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.38.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4513ab337297e978ef8dc16f9e1f2b28" + }, + { + "dataPath": "params_shard_203.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.39.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "447f09b7e224fdf48b8da66ee84ba249" + }, + { + "dataPath": "params_shard_204.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.38.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.38.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.38.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.38.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.39.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "7c9a48bfe145ae040f05e3beb43fca3e" + }, + { + "dataPath": "params_shard_205.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "6da334800c1a10770f562b8dc8fcb1d1" + }, + { + "dataPath": "params_shard_206.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.39.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "aadcbb481c59f1e5ab089003bf332828" + }, + { + "dataPath": "params_shard_207.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.39.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "986e61e47d9c424ea76c3f57bef2261a" + }, + { + "dataPath": "params_shard_208.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.39.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6284c36a04ea963b6481666e2ef172e2" + }, + { + "dataPath": "params_shard_209.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "611a43da0f37d5a08e5ecee62a9644ee" + }, + { + "dataPath": "params_shard_210.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.40.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "0239c3e369ff6da2d7054d461bc20282" + }, + { + "dataPath": "params_shard_211.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.40.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "4633edeec94f7449bfdf72f3cb312636" + }, + { + "dataPath": "params_shard_212.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.40.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "cd62566ece313361d60ec96ac8ff1516" + }, + { + "dataPath": "params_shard_213.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.39.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.39.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.39.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.39.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.40.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "95ba62b1d6ef06a4338e140403b2e418" + }, + { + "dataPath": "params_shard_214.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.4.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "312d15fe8943a20b2b9e190b287cc691" + }, + { + "dataPath": "params_shard_215.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "cd85815c081365537d748bcd69fe6eaf" + }, + { + "dataPath": "params_shard_216.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.4.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "c44d4a7008cb8a11a5d7aa6f6aa619dd" + }, + { + "dataPath": "params_shard_217.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d9df3855fde1e25f451d5bd6cc979da4" + }, + { + "dataPath": "params_shard_218.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.40.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.4.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.4.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.4.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.5.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "9b2a5daefd4e57bba94ce9afe93e2e03" + }, + { + "dataPath": "params_shard_219.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "7f7a4e61fc9fc4ab6c736241e3f3797b" + }, + { + "dataPath": "params_shard_220.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.5.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "610b8958ac210cf110d13f2ecb95c646" + }, + { + "dataPath": "params_shard_221.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.5.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "8627e5e3fd1ff22c3554ddc16a1eac97" + }, + { + "dataPath": "params_shard_222.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.5.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "502a2af874a88056ded5238a7f553757" + }, + { + "dataPath": "params_shard_223.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a223a8282810229fa631907cbfd8a0d4" + }, + { + "dataPath": "params_shard_224.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.5.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.5.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.5.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.5.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.6.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "b713c990926afb9280389ce96ff28649" + }, + { + "dataPath": "params_shard_225.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "ee60eef2440ac2c91d05cb122591d84b" + }, + { + "dataPath": "params_shard_226.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.6.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "392ce9f415de35e5ebcb49eba7b1cee4" + }, + { + "dataPath": "params_shard_227.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.6.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a69965b8177b3e45c0c6012b89ab69ee" + }, + { + "dataPath": "params_shard_228.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.6.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "ca16d3f0f37798d05983647343d46483" + }, + { + "dataPath": "params_shard_229.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.7.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5f5e2ef42a48d61496976bce132ef7b0" + }, + { + "dataPath": "params_shard_230.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "da603b0d53296a6fffcb059e79199f6c" + }, + { + "dataPath": "params_shard_231.bin", + "format": "raw-shard", + "nbytes": 29392896, + "records": [ + { + "name": "model.layers.6.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.6.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.6.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.6.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.7.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + }, + { + "name": "model.layers.40.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 29376512 + } + ], + "md5sum": "85b901b16e4c144f7f08127b8700830f" + }, + { + "dataPath": "params_shard_232.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.41.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "e0b699ef5cd313d74e2ef0d5b06efa8c" + }, + { + "dataPath": "params_shard_233.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "15ace8f934b32e21c4e64ede2792f97c" + }, + { + "dataPath": "params_shard_234.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.41.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "27647c8b4d4b1d2ebe4e339c9be24bff" + }, + { + "dataPath": "params_shard_235.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.41.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "2a117a6c33e991ade9fa5eaae95654a6" + }, + { + "dataPath": "params_shard_236.bin", + "format": "raw-shard", + "nbytes": 29409280, + "records": [ + { + "name": "model.layers.40.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.40.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.41.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14696448 + }, + { + "name": "model.layers.41.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 14712832 + }, + { + "name": "model.layers.41.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 29392896 + } + ], + "md5sum": "26f6ec958539dee46b604e191af66830" + }, + { + "dataPath": "params_shard_237.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.41.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d08318fffb352d2d5e4836ab753d933e" + }, + { + "dataPath": "params_shard_238.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.42.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6ae89299e548251c47a14d03b8ca4331" + }, + { + "dataPath": "params_shard_239.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "e3cb5f0063faab8af0f50c83d2f1cf82" + }, + { + "dataPath": "params_shard_240.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.42.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "6c707b23d871e36ef90928551c90e92c" + }, + { + "dataPath": "params_shard_241.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.42.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "279b7685fb2c1bce23a14054be763f52" + }, + { + "dataPath": "params_shard_242.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.42.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "82350aaffe13c2f92f52ce1ff141fd15" + }, + { + "dataPath": "params_shard_243.bin", + "format": "raw-shard", + "nbytes": 29392896, + "records": [ + { + "name": "model.layers.41.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 0 + }, + { + "name": "model.layers.41.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 5242880 + }, + { + "name": "model.layers.42.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9437184 + }, + { + "name": "model.layers.42.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9453568 + }, + { + "name": "model.layers.42.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + }, + { + "name": "model.layers.42.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24150016 + } + ], + "md5sum": "603c1dfcc04a16793f67df645ece3186" + }, + { + "dataPath": "params_shard_244.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.43.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "9b9bda85bba5b9d1dfaa24174b0bde0e" + }, + { + "dataPath": "params_shard_245.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.43.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "c13902e118cabef8b3c29b03a919c40c" + }, + { + "dataPath": "params_shard_246.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.43.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e3aee1c46a4d55fdc38e70ba1ff3c236" + }, + { + "dataPath": "params_shard_247.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.43.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "cb9b7213cd3880adc4ff787b8b985893" + }, + { + "dataPath": "params_shard_248.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.43.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2d9b3d726fadb01914418766d3059810" + }, + { + "dataPath": "params_shard_249.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.44.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "30649fbb5ee81b104e34f440828e9f56" + }, + { + "dataPath": "params_shard_250.bin", + "format": "raw-shard", + "nbytes": 28360704, + "records": [ + { + "name": "model.layers.42.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.43.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 4194304 + }, + { + "name": "model.layers.43.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 9437184 + }, + { + "name": "model.layers.43.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13631488 + }, + { + "name": "model.layers.43.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 13647872 + }, + { + "name": "model.layers.43.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 28327936 + }, + { + "name": "model.layers.44.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 28344320 + } + ], + "md5sum": "a22f6a80d3bf72f17e4bb05cc00dac89" + }, + { + "dataPath": "params_shard_251.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "925e92485572f02501fa8df6ae823e84" + }, + { + "dataPath": "params_shard_252.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.44.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "3b5e0f386c459f6d26847b5fa50b0bc2" + }, + { + "dataPath": "params_shard_253.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.44.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c29361b41e2ebcb12efe661e205a4b7d" + }, + { + "dataPath": "params_shard_254.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.44.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3994b8e5143173c645b59ee70997fb7f" + }, + { + "dataPath": "params_shard_255.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.45.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d55d48c89c2ad2c48acd781f6a5c3870" + }, + { + "dataPath": "params_shard_256.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.44.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.44.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.44.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.44.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.45.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "d72e1aa0a0d679e5dd779ed63661acd3" + }, + { + "dataPath": "params_shard_257.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.45.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "484ffdd8a6e367e0299cf99a2d93a911" + }, + { + "dataPath": "params_shard_258.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.45.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "5e78453ac4b6898c18a622c44b759c31" + }, + { + "dataPath": "params_shard_259.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.45.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "75f3d0d735fa6b177a15acbc5477792a" + }, + { + "dataPath": "params_shard_260.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.45.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "030b747be4e533042bbb6bbd923eb57b" + }, + { + "dataPath": "params_shard_261.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.46.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "2bcab80668ba1a2680749ca5f08e6167" + }, + { + "dataPath": "params_shard_262.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.46.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e07fd9a67e88de79539cbee359d65842" + }, + { + "dataPath": "params_shard_263.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.45.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.45.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.45.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.45.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.46.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "6825697de8400da0f51c58e520969b64" + }, + { + "dataPath": "params_shard_264.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.46.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f540b7ed798ad0433f8fc3221ae7adda" + }, + { + "dataPath": "params_shard_265.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "32cc852243db0bb985446480358d4b31" + }, + { + "dataPath": "params_shard_266.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.46.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "485cb9deff9f73c36d8c521e01cc2421" + }, + { + "dataPath": "params_shard_267.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.47.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "b59cbc5e2dd990c1c6d51910e8fab254" + }, + { + "dataPath": "params_shard_268.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.46.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.46.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.46.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.46.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.47.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "9369cf402547097bafe92be280517c4f" + }, + { + "dataPath": "params_shard_269.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.47.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "62fc622c609d8c2875197629015bd43b" + }, + { + "dataPath": "params_shard_270.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.47.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "134229812dc8ea59c598fe9db04bcbdf" + }, + { + "dataPath": "params_shard_271.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.47.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "3908d57710dcbcb8c65b2fc08ef0cd6d" + }, + { + "dataPath": "params_shard_272.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.47.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c14bbfcee11c9147278353f1ed173722" + }, + { + "dataPath": "params_shard_273.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.48.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6bec7f4c8a66390eee95284fb820c9c2" + }, + { + "dataPath": "params_shard_274.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.47.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.47.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.47.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.47.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.48.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "dd06d714306ae73943a08091009702ca" + }, + { + "dataPath": "params_shard_275.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "612d308bea33830d2acacc941447fe11" + }, + { + "dataPath": "params_shard_276.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.48.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "c40b0520d08cfbf60c178542c410d747" + }, + { + "dataPath": "params_shard_277.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.48.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "48d8ab593a0ec51662ad942b2675f47c" + }, + { + "dataPath": "params_shard_278.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.48.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f18725212549016f8960d8d0158e16ea" + }, + { + "dataPath": "params_shard_279.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.49.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "dc26acb7fb969faf35970f3846892ab9" + }, + { + "dataPath": "params_shard_280.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.49.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "3bb11375a144cd597b9437ac51d5edb4" + }, + { + "dataPath": "params_shard_281.bin", + "format": "raw-shard", + "nbytes": 29392896, + "records": [ + { + "name": "model.layers.48.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.48.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.48.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.48.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.49.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + }, + { + "name": "model.layers.49.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 29376512 + } + ], + "md5sum": "b98c61e93551e3933c1dba255d831e0d" + }, + { + "dataPath": "params_shard_282.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.49.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "0a5f95d7065847e32578d10133d7a6e2" + }, + { + "dataPath": "params_shard_283.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.49.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "bd7b8d940d6ee79e66a9195e02466a0d" + }, + { + "dataPath": "params_shard_284.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.49.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "38b3811d75ba982f09c0f75e9e352228" + }, + { + "dataPath": "params_shard_285.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.50.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "09747ed83783093e0d21bafae8784031" + }, + { + "dataPath": "params_shard_286.bin", + "format": "raw-shard", + "nbytes": 18907136, + "records": [ + { + "name": "model.layers.49.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.49.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.49.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 14696448 + }, + { + "name": "model.layers.50.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + } + ], + "md5sum": "630e0ba02288ba4a1b21158dc63be0d1" + }, + { + "dataPath": "params_shard_287.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.50.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "813880a78241f4a69189d366860b8fa3" + }, + { + "dataPath": "params_shard_288.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.50.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "d1945190595900514d297e77e46dc967" + }, + { + "dataPath": "params_shard_289.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.50.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "e796681bfa604ff8ac4b482205602b17" + }, + { + "dataPath": "params_shard_290.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.50.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "16e6fa48a172a339e8be4df9ad057cbe" + }, + { + "dataPath": "params_shard_291.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.51.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "32dd2309fd911c539b38165ad36e8193" + }, + { + "dataPath": "params_shard_292.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.50.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.50.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.50.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.50.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.51.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "2f741d266ebfc3d9bd63d7c79a88b9fa" + }, + { + "dataPath": "params_shard_293.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.51.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "513f1706b41a396a3bf00f5fad8b7029" + }, + { + "dataPath": "params_shard_294.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.51.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "1d23a0a73c4dceb397b200eedfdf9287" + }, + { + "dataPath": "params_shard_295.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.51.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "0a8874458a3dc4172637e6ff96a8f285" + }, + { + "dataPath": "params_shard_296.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.51.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "9559b57650af15dc14d5ca78edfa009f" + }, + { + "dataPath": "params_shard_297.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.52.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "fcb3f4654a9819d1067b81aab811cc49" + }, + { + "dataPath": "params_shard_298.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.51.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.51.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.51.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.51.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.52.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "ca4fd120f81a490bd389a7492f8c4ead" + }, + { + "dataPath": "params_shard_299.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.52.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f411563f96db2a2777678b2b079bcb05" + }, + { + "dataPath": "params_shard_300.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.52.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "01a6e3cb09e84cd453ff99e5d49685ed" + }, + { + "dataPath": "params_shard_301.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.52.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "50d663b302c1f8daa300355097149106" + }, + { + "dataPath": "params_shard_302.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.52.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "cbe37b25b133c8d536f87a7797256ceb" + }, + { + "dataPath": "params_shard_303.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.53.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "dc2352b91b3ecc0685259beb753cb870" + }, + { + "dataPath": "params_shard_304.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.52.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.52.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.52.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.52.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.53.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "78497c851caa6599b3d40d13dfbc76db" + }, + { + "dataPath": "params_shard_305.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "66432f11562d5c5949f2a8cfdf290b65" + }, + { + "dataPath": "params_shard_306.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.53.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "07e264f07db20eecd2b5099c76c7ffb0" + }, + { + "dataPath": "params_shard_307.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.53.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5c0e6bc59c33b760790e6fc8a8f11b67" + }, + { + "dataPath": "params_shard_308.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.53.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "53b8164a33b080254f7a2626a4cdf534" + }, + { + "dataPath": "params_shard_309.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.54.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "12aeacde69bf6ca6cca041d137659e7f" + }, + { + "dataPath": "params_shard_310.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.54.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "d72d78f33629d3af30eebfe4336e4ce8" + }, + { + "dataPath": "params_shard_311.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.54.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "2818532139a0a32eb6ced01db1f76c32" + }, + { + "dataPath": "params_shard_312.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.54.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "93f357bd6956c6cb788f4bc1f0ba09b5" + }, + { + "dataPath": "params_shard_313.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.53.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.53.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.53.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.53.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.54.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "812177f5fe51b74c4f4b87b1bcd434c3" + }, + { + "dataPath": "params_shard_314.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.54.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f5814392b91341b332e26aa632f7b159" + }, + { + "dataPath": "params_shard_315.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.55.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "4613eec841d47fe1da671af1d3aea006" + }, + { + "dataPath": "params_shard_316.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.54.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.54.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.54.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.54.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.55.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "3028a9204f19dac2059ddaf6c65f3dcc" + }, + { + "dataPath": "params_shard_317.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "6dc8aba0a90d6bbbc604a1e9198f17fa" + }, + { + "dataPath": "params_shard_318.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.55.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "3f2d7774ff00fcfb3cf7f9c96f38a3fd" + }, + { + "dataPath": "params_shard_319.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.55.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "03e17065679c7a7e87f716cd53c52dbf" + }, + { + "dataPath": "params_shard_320.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.55.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "c39a8b6fdfc1d2ed9e8b109e4dcdc690" + }, + { + "dataPath": "params_shard_321.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.56.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2250fb592255cecf3468881228b520a1" + }, + { + "dataPath": "params_shard_322.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.55.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.55.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.55.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.55.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.56.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "e37cb0afd5c1ac4dd09faaf556e9b800" + }, + { + "dataPath": "params_shard_323.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.56.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "e2a9734fd04cdd0920f74fad848af8d7" + }, + { + "dataPath": "params_shard_324.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.56.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "a62c36a9467280cd58a56bc1437f80c2" + }, + { + "dataPath": "params_shard_325.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.56.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d054e280d65b5d5539d510838ff5fc7e" + }, + { + "dataPath": "params_shard_326.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.56.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "f5d030d3fe168ace9f69c99ed539d158" + }, + { + "dataPath": "params_shard_327.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "15e588b743ea3feb363d53a6569386b5" + }, + { + "dataPath": "params_shard_328.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.57.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "9fa119406f131f2ec4a2fef13453f3e2" + }, + { + "dataPath": "params_shard_329.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.57.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "996e5b344c2ecb2c2464141106f7d3b2" + }, + { + "dataPath": "params_shard_330.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.57.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "77621618de9eb06190bd0e8822bc874f" + }, + { + "dataPath": "params_shard_331.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.56.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.56.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.56.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.56.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.57.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "f7aff98ed4c36143bcafcc832d416b07" + }, + { + "dataPath": "params_shard_332.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.57.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "d5ad87ed06fe42170112a21f888ced7b" + }, + { + "dataPath": "params_shard_333.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.58.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2534880021f12296e0ac1bdce8fb7ace" + }, + { + "dataPath": "params_shard_334.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.57.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.57.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.57.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.57.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.58.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "d6384e89e55d463fafc85c73c5555ce7" + }, + { + "dataPath": "params_shard_335.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.58.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "6a344e4b72423f1ca2e3dbfeb617e0ee" + }, + { + "dataPath": "params_shard_336.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.58.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "fa75ed3b5268040a3968681796ebe7fe" + }, + { + "dataPath": "params_shard_337.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.58.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "a710ed6d616b70bab45a4d4d2f0b8858" + }, + { + "dataPath": "params_shard_338.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.58.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "be5cd1c680243a5bc9bf149f3d49ac55" + }, + { + "dataPath": "params_shard_339.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.59.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "acb2c5b13f1152ebaeb65d8421152598" + }, + { + "dataPath": "params_shard_340.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.58.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.58.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.58.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.58.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.59.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "38528de8d257278920266549d574c538" + }, + { + "dataPath": "params_shard_341.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "9d092418250ff6ba0967be48aa90d894" + }, + { + "dataPath": "params_shard_342.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.59.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "5784bb42c68488ae642712d04440aae9" + }, + { + "dataPath": "params_shard_343.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.59.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5cfcceea4b4ffa7ac54e0589df516444" + }, + { + "dataPath": "params_shard_344.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.59.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3a5b45db7f047fa3f4a2df3f6b33fa12" + }, + { + "dataPath": "params_shard_345.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.60.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "b8b395d98e2ef5365bec7bc7cfef1612" + }, + { + "dataPath": "params_shard_346.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.60.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e2224fe1a4c433b74fcd4dd4ce0b643d" + }, + { + "dataPath": "params_shard_347.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.59.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.59.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.59.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.59.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.60.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "a877a11e690d611db7e809ccc010df16" + }, + { + "dataPath": "params_shard_348.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.60.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6ebf3d60704a5b62e7eaf47003ac4425" + }, + { + "dataPath": "params_shard_349.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.60.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "e314fd6d72f7f7775f719b9cbbeab54e" + }, + { + "dataPath": "params_shard_350.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.60.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "ef33db5e4fad4153a590c34613668878" + }, + { + "dataPath": "params_shard_351.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.61.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "69d46f887596bf8a405d1931e24746dc" + }, + { + "dataPath": "params_shard_352.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.60.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.60.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.60.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.60.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.61.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "60800eb98d00e10336b56bd79d3507ad" + }, + { + "dataPath": "params_shard_353.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.61.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "a5095532702ce08488d03b3c875f52c3" + }, + { + "dataPath": "params_shard_354.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.61.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "8f25fe64665c4db87ce1b160ad2510dc" + }, + { + "dataPath": "params_shard_355.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.61.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "c0175d43d36ca215fb428151815177bc" + }, + { + "dataPath": "params_shard_356.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.61.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4ca76dc211ebf1049014ced630154795" + }, + { + "dataPath": "params_shard_357.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.62.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "9c7b3baed3d989508be8bb688d4f8b25" + }, + { + "dataPath": "params_shard_358.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.61.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.61.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.61.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.61.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.62.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "f35827083ddd77fca38cae7c05a80b7f" + }, + { + "dataPath": "params_shard_359.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.62.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "97cf1f08a98a192e673389133d97565b" + }, + { + "dataPath": "params_shard_360.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.62.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "80eee7d649ee5ec253a15db9ff03c87a" + }, + { + "dataPath": "params_shard_361.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.62.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "0687a23e5df755f5fae4b4bf0d33e651" + }, + { + "dataPath": "params_shard_362.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.62.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5a33463dae4791ba7cf6e24846656fcb" + }, + { + "dataPath": "params_shard_363.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.63.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "4e4aeb9f8937f8652b90ec5da3248a4d" + }, + { + "dataPath": "params_shard_364.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.63.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "c013b120f5e03c774996421b35fd8fe3" + }, + { + "dataPath": "params_shard_365.bin", + "format": "raw-shard", + "nbytes": 29392896, + "records": [ + { + "name": "model.layers.62.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.62.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.62.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.62.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.63.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + }, + { + "name": "model.layers.63.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 29376512 + } + ], + "md5sum": "9cb4b94b2bfe02b77f43d63a015cbc7d" + }, + { + "dataPath": "params_shard_366.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.63.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "fc52ef1fc43899284235fc835d11b2f5" + }, + { + "dataPath": "params_shard_367.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.63.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "cfdb6b7f29f35a72908576a0deea51bf" + }, + { + "dataPath": "params_shard_368.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.63.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "2d6f26701aa0bd64a4f469c67adddd91" + }, + { + "dataPath": "params_shard_369.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.64.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6e6cf74a8750b69c9438a70b28b4c5c6" + }, + { + "dataPath": "params_shard_370.bin", + "format": "raw-shard", + "nbytes": 18907136, + "records": [ + { + "name": "model.layers.63.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.63.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.63.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 14696448 + }, + { + "name": "model.layers.64.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + } + ], + "md5sum": "e77231e1d7a63dbd0c283e0e299d7cee" + }, + { + "dataPath": "params_shard_371.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.64.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "8cfacee7717f20c9f210a6940f131ece" + }, + { + "dataPath": "params_shard_372.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.64.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "4b1208c699d577b291b321a18340bfb7" + }, + { + "dataPath": "params_shard_373.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.64.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "6c7e0484293eaf1709f3acff23e889b8" + }, + { + "dataPath": "params_shard_374.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.64.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "a272d67faa02f1e776d2bcbd44431f99" + }, + { + "dataPath": "params_shard_375.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.65.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "29af1b7176571bdf9e8fadaedd00c6ce" + }, + { + "dataPath": "params_shard_376.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.64.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.64.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.64.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.64.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.65.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "9dee4c49994a5b06a3f83f675231ad3c" + }, + { + "dataPath": "params_shard_377.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.65.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "fc08de8a7188f6662d23178073b4c292" + }, + { + "dataPath": "params_shard_378.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.65.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "9fd09dfa0374ae71ffe9827670be22de" + }, + { + "dataPath": "params_shard_379.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.65.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "6ae50bd5c16a558d67340b93fe1d0455" + }, + { + "dataPath": "params_shard_380.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.65.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "5077c4933ea3a8bec32683a2a06f6a7e" + }, + { + "dataPath": "params_shard_381.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.66.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "e2c7b28f3fb763f539eb433a4f6c4866" + }, + { + "dataPath": "params_shard_382.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.65.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.65.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.65.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.65.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.66.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "fd57e595485f0d0c92f88d848795ecc6" + }, + { + "dataPath": "params_shard_383.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.66.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "fcfaee9b58d78af675c7574aaa24adbc" + }, + { + "dataPath": "params_shard_384.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.66.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "cf49bbd579662942ca83a4950d98279d" + }, + { + "dataPath": "params_shard_385.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.66.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "0415366845b8abb6a0e7497f1f37e1af" + }, + { + "dataPath": "params_shard_386.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.66.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "2badec1e6ff026f087d64aae76dc8a7f" + }, + { + "dataPath": "params_shard_387.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.67.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "ad921ffff4c57ca5abf903c9e8b31368" + }, + { + "dataPath": "params_shard_388.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.66.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.66.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.66.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.66.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.67.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "31b2278b6ef2d7a888530924a8ba80af" + }, + { + "dataPath": "params_shard_389.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.67.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f7562073e5efc295cde7e7c4dc34ff76" + }, + { + "dataPath": "params_shard_390.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.67.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "fa8f9eeb77551074879128836716d5a2" + }, + { + "dataPath": "params_shard_391.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.67.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "6a1faf6117c008f458143d345877bc21" + }, + { + "dataPath": "params_shard_392.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.67.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6faea48295a92ec521de351560cb9812" + }, + { + "dataPath": "params_shard_393.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.68.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "b35c16726ab4146eaab988bdf183baf4" + }, + { + "dataPath": "params_shard_394.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.68.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "ec11dc2bd846c555cc4d9911b10b6d56" + }, + { + "dataPath": "params_shard_395.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.68.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "60b88a5b63f63d4840f97fa96a541863" + }, + { + "dataPath": "params_shard_396.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.68.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "178797fc6ec1c2b7eb3ab038e867e042" + }, + { + "dataPath": "params_shard_397.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.67.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.67.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.67.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.67.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.68.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "1a86057eb788ffb69a7b58645ce31975" + }, + { + "dataPath": "params_shard_398.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.68.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "6140320058499a5dabe2a604f2a7afbc" + }, + { + "dataPath": "params_shard_399.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.69.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "cc4b1053b00a4c90a44c5c5d60b7ac1e" + }, + { + "dataPath": "params_shard_400.bin", + "format": "raw-shard", + "nbytes": 18923520, + "records": [ + { + "name": "model.layers.68.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.68.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.68.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.68.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.69.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18907136 + } + ], + "md5sum": "4a5987ff6c33d42911644eac4be95914" + }, + { + "dataPath": "params_shard_401.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.69.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "5d4b986df9178d1720b213f2754bc3c2" + }, + { + "dataPath": "params_shard_402.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.69.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "a72f8a5c8cc98120f402bceef6c4f611" + }, + { + "dataPath": "params_shard_403.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.69.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d46ed7381873555826f8af85c3eaacc6" + }, + { + "dataPath": "params_shard_404.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.69.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "92a51d8a2a6f393c5e436678effd5ac4" + }, + { + "dataPath": "params_shard_405.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.70.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "2f46dad5d10053363c175a0dc743788c" + }, + { + "dataPath": "params_shard_406.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.69.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.69.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.69.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.69.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.70.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "31012690a77c2cf6a123da8e241a4487" + }, + { + "dataPath": "params_shard_407.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.70.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "7bbec664bdba7a60f20ce603b22e9ee3" + }, + { + "dataPath": "params_shard_408.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.70.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "cf0147e7d363a4c301ba083c51f8498d" + }, + { + "dataPath": "params_shard_409.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.70.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "3651418f3692dd78802c30d3bac7cb0c" + }, + { + "dataPath": "params_shard_410.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.70.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "03809809491d447579a19c695e2e4055" + }, + { + "dataPath": "params_shard_411.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.71.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "bda154c10f3b5b764bbe7678210320c4" + }, + { + "dataPath": "params_shard_412.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.71.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "919dfe3b876c70860aa8a60b829ffa91" + }, + { + "dataPath": "params_shard_413.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.71.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "4a1ec0876a8c259997d65e661caf2150" + }, + { + "dataPath": "params_shard_414.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.71.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "3105347278772517a5242b921f64105b" + }, + { + "dataPath": "params_shard_415.bin", + "format": "raw-shard", + "nbytes": 29376512, + "records": [ + { + "name": "model.layers.70.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.70.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.70.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.70.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.71.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + } + ], + "md5sum": "4b9e55565312190d000559aa4cecb405" + }, + { + "dataPath": "params_shard_416.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.7.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "23ab1840d6bfca5000426bc5ad2f32bb" + }, + { + "dataPath": "params_shard_417.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "d61abe6d5bb58bfb86253d5bbec1f170" + }, + { + "dataPath": "params_shard_418.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.7.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "b5ab141f4fa20964c2333483bed10677" + }, + { + "dataPath": "params_shard_419.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.7.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "d44c08bb284f78702581c8ee0ead177e" + }, + { + "dataPath": "params_shard_420.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "f9793cddff1a3159a8d5d7d35131efcf" + }, + { + "dataPath": "params_shard_421.bin", + "format": "raw-shard", + "nbytes": 23117824, + "records": [ + { + "name": "model.layers.71.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.7.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 4194304 + }, + { + "name": "model.layers.7.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 4210688 + }, + { + "name": "model.layers.7.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + }, + { + "name": "model.layers.7.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 18907136 + }, + { + "name": "model.layers.8.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 23101440 + } + ], + "md5sum": "f5accdf618ad71b1594ac010d48ddc73" + }, + { + "dataPath": "params_shard_422.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "40ab05b40cd28de7ddef67780e1d3532" + }, + { + "dataPath": "params_shard_423.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.8.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "ed607969095f9a094b881a063f6a4aea" + }, + { + "dataPath": "params_shard_424.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.8.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "475f1abc3d6122568620badefba7d0e3" + }, + { + "dataPath": "params_shard_425.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.8.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "703a5cad77426d7871d5eda29fd19d18" + }, + { + "dataPath": "params_shard_426.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "533a183a6463248df786086dea3642d3" + }, + { + "dataPath": "params_shard_427.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.8.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.8.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.8.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.8.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.9.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "5721e119156526370b5af7001bfcadb2" + }, + { + "dataPath": "params_shard_428.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "58a9157ef37373093b81c48a7d76b9a7" + }, + { + "dataPath": "params_shard_429.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.9.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "437f582265cb2e2e36468cc598ea5c36" + }, + { + "dataPath": "params_shard_430.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.9.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1f10e8ca8a656ffc23d36b42574704f4" + }, + { + "dataPath": "params_shard_431.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.9.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "34a9c4ee49a3dce0dcce1c3307bcea2f" + }, + { + "dataPath": "params_shard_432.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.71.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "32a307533d46eda999c27b3e6fb3f554" + }, + { + "dataPath": "params_shard_433.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.9.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.9.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.9.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.9.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.71.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "ec163c777a536db1ebea878ba7f574ac" + }, + { + "dataPath": "params_shard_434.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.72.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "602c328163d1aa93fa3d4067041acbec" + }, + { + "dataPath": "params_shard_435.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.72.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "5c9dc37c31d94971ca1f7d4a11012979" + }, + { + "dataPath": "params_shard_436.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.72.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "d335c50cbfa7393cbb0bdc296c5a2d15" + }, + { + "dataPath": "params_shard_437.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.72.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "58cddc5eb10df28cd8291c75bdc725d2" + }, + { + "dataPath": "params_shard_438.bin", + "format": "raw-shard", + "nbytes": 29409280, + "records": [ + { + "name": "model.layers.71.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.71.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.72.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14696448 + }, + { + "name": "model.layers.72.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 14712832 + }, + { + "name": "model.layers.72.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 29392896 + } + ], + "md5sum": "4e554ad7717bb0eef6da5f990d03ae7c" + }, + { + "dataPath": "params_shard_439.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.72.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b3df8309450717f316ad17eedd1e9ba0" + }, + { + "dataPath": "params_shard_440.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.73.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "a6a2ccc472da2c03cdff72c6f29e0b0d" + }, + { + "dataPath": "params_shard_441.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.73.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "00ae088c8c92e1666e97a698137a9036" + }, + { + "dataPath": "params_shard_442.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.73.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "616899c26d69db6367bc995e55b3091c" + }, + { + "dataPath": "params_shard_443.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.73.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "7e32e1bbbfdba3cd2801779fd51bc7fe" + }, + { + "dataPath": "params_shard_444.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.73.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "e8e0235cfd44299cbca5b8a7296ab563" + }, + { + "dataPath": "params_shard_445.bin", + "format": "raw-shard", + "nbytes": 29392896, + "records": [ + { + "name": "model.layers.72.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 0 + }, + { + "name": "model.layers.72.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 5242880 + }, + { + "name": "model.layers.73.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 9437184 + }, + { + "name": "model.layers.73.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 9453568 + }, + { + "name": "model.layers.73.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + }, + { + "name": "model.layers.73.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24150016 + } + ], + "md5sum": "ea0757caaa72b004a01fd3cc3f78f427" + }, + { + "dataPath": "params_shard_446.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.74.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "52fcf3f7ff11c693c65562ebc1261a37" + }, + { + "dataPath": "params_shard_447.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.74.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "6bc14405f3f765c65d01b7387359a41f" + }, + { + "dataPath": "params_shard_448.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.74.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "0ca3100d1d580291d69d39c7777c3eaf" + }, + { + "dataPath": "params_shard_449.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.74.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "9cf640105398b0ff78ac75d0adebf349" + }, + { + "dataPath": "params_shard_450.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.74.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "cd0c6da68dc593f34cb68cf0eeecfe13" + }, + { + "dataPath": "params_shard_451.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.75.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "1c32b69574803a4caa3b9a23f68755c8" + }, + { + "dataPath": "params_shard_452.bin", + "format": "raw-shard", + "nbytes": 28360704, + "records": [ + { + "name": "model.layers.73.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 0 + }, + { + "name": "model.layers.74.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 4194304 + }, + { + "name": "model.layers.74.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 9437184 + }, + { + "name": "model.layers.74.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 13631488 + }, + { + "name": "model.layers.74.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 13647872 + }, + { + "name": "model.layers.74.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 28327936 + }, + { + "name": "model.layers.75.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 28344320 + } + ], + "md5sum": "be65c977f135a3f3caa6e7fd30967234" + }, + { + "dataPath": "params_shard_453.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.75.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "d813ae28afb49e8c4d23cc8684abf65a" + }, + { + "dataPath": "params_shard_454.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.75.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "5b2dca70b38ad5ea7cdeab2fdf04943a" + }, + { + "dataPath": "params_shard_455.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.75.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "52f81e75d85cf03b83f5bff3c5e9674c" + }, + { + "dataPath": "params_shard_456.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.75.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "4513310339006bb26b5e8963ddf94a51" + }, + { + "dataPath": "params_shard_457.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.76.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "197ddcba4be804e4a2994f9ac9814a50" + }, + { + "dataPath": "params_shard_458.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.75.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.75.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.75.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.75.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.76.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "2761322de58ab2948dd8bde58c4a07ea" + }, + { + "dataPath": "params_shard_459.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.76.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "3aad17227408cee2a0991d2a82f8dcc7" + }, + { + "dataPath": "params_shard_460.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.76.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "b1215a7f45be8ae59b13e8e6c3a63394" + }, + { + "dataPath": "params_shard_461.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.76.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "5b49d51fc7c917670890fe8b40e90b74" + }, + { + "dataPath": "params_shard_462.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.76.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "b147c59bba0ab00ca3abed2b91c7b834" + }, + { + "dataPath": "params_shard_463.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.77.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "1a64f1a0ab6431373c74967deaa598c7" + }, + { + "dataPath": "params_shard_464.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.77.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "743470c6725473509c00fc8f65004e18" + }, + { + "dataPath": "params_shard_465.bin", + "format": "raw-shard", + "nbytes": 29392896, + "records": [ + { + "name": "model.layers.76.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.76.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.76.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.76.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.77.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 24133632 + }, + { + "name": "model.layers.77.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 29376512 + } + ], + "md5sum": "ebed01ffdf40d75273b27bb785a3ca1b" + }, + { + "dataPath": "params_shard_466.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.77.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "47ec3d773eafe878cb0b4da994f12005" + }, + { + "dataPath": "params_shard_467.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.77.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "2db1c5e77a08592ae81a932dbf80a632" + }, + { + "dataPath": "params_shard_468.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.77.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "566ee6fe0f671b5210206765b87c9a58" + }, + { + "dataPath": "params_shard_469.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.78.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "49ab96471bfaf3e2f4209682034e1c91" + }, + { + "dataPath": "params_shard_470.bin", + "format": "raw-shard", + "nbytes": 18907136, + "records": [ + { + "name": "model.layers.77.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.77.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.77.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 14696448 + }, + { + "name": "model.layers.78.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 18890752 + } + ], + "md5sum": "63bb03b15d6bbca4ea11064b68dbb165" + }, + { + "dataPath": "params_shard_471.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.78.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "f33e70d8bb6bad31c1c98f8de72447ad" + }, + { + "dataPath": "params_shard_472.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.78.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "ecfdd5fe19bff7ee1ec8707daf88cdfa" + }, + { + "dataPath": "params_shard_473.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.78.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "f3bdaff18b890904e1d2d09786ebf057" + }, + { + "dataPath": "params_shard_474.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.78.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "594f4f9c85a09c178d48ab97d733ae72" + }, + { + "dataPath": "params_shard_475.bin", + "format": "raw-shard", + "nbytes": 117440512, + "records": [ + { + "name": "model.layers.79.mlp.down_proj.q_weight", + "shape": [ + 8192, + 3584 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 117440512, + "byteOffset": 0 + } + ], + "md5sum": "665a175b1b8f3662edd9236375f0b674" + }, + { + "dataPath": "params_shard_476.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.78.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.78.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.78.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.78.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.layers.79.input_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "935e986e4ce36b6a5657419d41f798e0" + }, + { + "dataPath": "params_shard_477.bin", + "format": "raw-shard", + "nbytes": 234881024, + "records": [ + { + "name": "model.layers.79.mlp.gate_up_proj.q_weight", + "shape": [ + 57344, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 234881024, + "byteOffset": 0 + } + ], + "md5sum": "84247feb78e49c15fb975be222a314ce" + }, + { + "dataPath": "params_shard_478.bin", + "format": "raw-shard", + "nbytes": 29360128, + "records": [ + { + "name": "model.layers.79.mlp.gate_up_proj.q_scale", + "shape": [ + 57344, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 29360128, + "byteOffset": 0 + } + ], + "md5sum": "f7b3cedef17f6c3691cb319fa86faf56" + }, + { + "dataPath": "params_shard_479.bin", + "format": "raw-shard", + "nbytes": 41943040, + "records": [ + { + "name": "model.layers.79.self_attn.qkv_proj.q_weight", + "shape": [ + 10240, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 41943040, + "byteOffset": 0 + } + ], + "md5sum": "d6d839648d41468eebb3f491d6dd9e4f" + }, + { + "dataPath": "params_shard_480.bin", + "format": "raw-shard", + "nbytes": 33554432, + "records": [ + { + "name": "model.layers.79.self_attn.o_proj.q_weight", + "shape": [ + 8192, + 1024 + ], + "dtype": "uint32", + "format": "f32-to-bf16", + "nbytes": 33554432, + "byteOffset": 0 + } + ], + "md5sum": "66b2e53936ef7986e2b20978acc1f5f3" + }, + { + "dataPath": "params_shard_481.bin", + "format": "raw-shard", + "nbytes": 24150016, + "records": [ + { + "name": "model.layers.79.mlp.down_proj.q_scale", + "shape": [ + 8192, + 896 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 14680064, + "byteOffset": 0 + }, + { + "name": "model.layers.79.post_attention_layernorm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 14680064 + }, + { + "name": "model.layers.79.self_attn.qkv_proj.q_scale", + "shape": [ + 10240, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 5242880, + "byteOffset": 14696448 + }, + { + "name": "model.layers.79.self_attn.o_proj.q_scale", + "shape": [ + 8192, + 256 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 4194304, + "byteOffset": 19939328 + }, + { + "name": "model.norm.weight", + "shape": [ + 8192 + ], + "dtype": "float16", + "format": "f32-to-bf16", + "nbytes": 16384, + "byteOffset": 24133632 + } + ], + "md5sum": "a909ee7ac3e273bc6e38ecaad3b4e382" + } + ] +} \ No newline at end of file diff --git a/params_shard_10.bin b/params_shard_10.bin new file mode 100644 index 0000000000000000000000000000000000000000..205ca544dfba5d3e9ed93a6e93afd0fb368c19b6 --- /dev/null +++ b/params_shard_10.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e7c11e6f125942a81511c2d617db8b5c24abd108b7b907e2b2345b661248140 +size 29360128 diff --git a/params_shard_100.bin b/params_shard_100.bin new file mode 100644 index 0000000000000000000000000000000000000000..ef32d5dcf302150285061f6f35b2926dc4562a90 --- /dev/null +++ b/params_shard_100.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9aa06a9f997e2160cc98469df29d7c8038949f61a819c6afc1b342b459b3964c +size 33554432 diff --git a/params_shard_102.bin b/params_shard_102.bin new file mode 100644 index 0000000000000000000000000000000000000000..df1ddfb4128265eb5a045451d1dda1f078b7d9a0 --- /dev/null +++ b/params_shard_102.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5f93fc3a596459c6f342206abf7dc67acc611a1968ab83821a90c128cddaa2e +size 18907136 diff --git a/params_shard_104.bin b/params_shard_104.bin new file mode 100644 index 0000000000000000000000000000000000000000..506da6aa97230c84da720011e6645601d59ceec7 --- /dev/null +++ b/params_shard_104.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26e5f2c1ce7c9db8fa5be9f12ac6ea74ee76fe4082dda56b61c43fe31a1d259 +size 29360128 diff --git a/params_shard_105.bin b/params_shard_105.bin new file mode 100644 index 0000000000000000000000000000000000000000..944a504e2ab91fb26a69514545bd090405227049 --- /dev/null +++ b/params_shard_105.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff7669290efa2bc0b798cb1dfd958ccb936a7a613677c35f503c74ee010bfcc8 +size 41943040 diff --git a/params_shard_106.bin b/params_shard_106.bin new file mode 100644 index 0000000000000000000000000000000000000000..31d939460952c3f72e10f92d419400c151bdff2d --- /dev/null +++ b/params_shard_106.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad770f37bf991a921814b77c154046bcfd78632ece3465a0dc5298a82d79cf1 +size 33554432 diff --git a/params_shard_108.bin b/params_shard_108.bin new file mode 100644 index 0000000000000000000000000000000000000000..8852bbdf19b11e7cea48d59c7ea7dff8b8e42c2b --- /dev/null +++ b/params_shard_108.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:146ddf9941a3f17b4b5733aac17286daef6ee279eea3d07b5ee03701e67e2879 +size 24150016 diff --git a/params_shard_11.bin b/params_shard_11.bin new file mode 100644 index 0000000000000000000000000000000000000000..55471209beff9f7254f5d0f2f40279ffff154645 --- /dev/null +++ b/params_shard_11.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98502e87ece9c9af02c30cf99517ddcc9612b7b2b52574f0dfe7903ffad79265 +size 41943040 diff --git a/params_shard_110.bin b/params_shard_110.bin new file mode 100644 index 0000000000000000000000000000000000000000..31229be7d3339e18035eb1d66de0e3da0fb83553 --- /dev/null +++ b/params_shard_110.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4df06ad450a4f9eb5fc03096f17326bd6bd040b87d3be960d3a432e98123b99a +size 29360128 diff --git a/params_shard_111.bin b/params_shard_111.bin new file mode 100644 index 0000000000000000000000000000000000000000..b539cadb3ca0f4bea6fdbe46e2952cd16eed6435 --- /dev/null +++ b/params_shard_111.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bd780a05df1747a737ed081cedcce1dac4e472043e6c851bf4ca626cc184b3f +size 41943040 diff --git a/params_shard_112.bin b/params_shard_112.bin new file mode 100644 index 0000000000000000000000000000000000000000..17c6a5a6b71b45c5b195efd84e60dda2083ce4b8 --- /dev/null +++ b/params_shard_112.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5ebefe25a9ad006138d72437d1779c04bd3462b8acaa212fd56d291967f8a67 +size 33554432 diff --git a/params_shard_114.bin b/params_shard_114.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0893acdd40d2bcf623c49ee93459ecb964c3ea6 --- /dev/null +++ b/params_shard_114.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3d42d81c080fccd6319c3543f33db7c425a0fda19b03e0a5f3bf360d1a77a2 +size 24150016 diff --git a/params_shard_116.bin b/params_shard_116.bin new file mode 100644 index 0000000000000000000000000000000000000000..da332bbd0a32b8057ead92fb5b59395be484a40d --- /dev/null +++ b/params_shard_116.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e2f16d0f1cd2be9ffdba0179384bc800a116a048b5aa6af7ba83649ca70a549 +size 29360128 diff --git a/params_shard_117.bin b/params_shard_117.bin new file mode 100644 index 0000000000000000000000000000000000000000..b96a0b7ea72ffd03edcef838d9c258de5bac0637 --- /dev/null +++ b/params_shard_117.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dc684f8ae8b9b978a2dfbdabbde32769de25f0a38ae0c75a16bcb906302ed5f +size 41943040 diff --git a/params_shard_12.bin b/params_shard_12.bin new file mode 100644 index 0000000000000000000000000000000000000000..8058431c7ed32e3fba96005258dfd4f406199bb9 --- /dev/null +++ b/params_shard_12.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d906d87d2488863efd37445169e74cdf2b377427574b7a308bba1f625a570b4 +size 33554432 diff --git a/params_shard_120.bin b/params_shard_120.bin new file mode 100644 index 0000000000000000000000000000000000000000..5f9d1b101bdc0384e0efdf0eff0f222cf2855da3 --- /dev/null +++ b/params_shard_120.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cd15bf46983be2362edac2b3acc9c35552c0a817ba844db67ebb4ee2059b3fd +size 24150016 diff --git a/params_shard_122.bin b/params_shard_122.bin new file mode 100644 index 0000000000000000000000000000000000000000..2639efcf0ee832d76dae858ec5b311f80bf0fa9b --- /dev/null +++ b/params_shard_122.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd4904f6a6ffd438d301f4e0e56b8040b3214707c9786a0b44d1a21248663d8d +size 29360128 diff --git a/params_shard_123.bin b/params_shard_123.bin new file mode 100644 index 0000000000000000000000000000000000000000..743470ddfd32901aef12e9ea0e0747b80f96e79e --- /dev/null +++ b/params_shard_123.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca45b423fb437b9cdd5c1c16a8d8faf19ea32c6ed3e5cfeb7f2416f00faba619 +size 41943040 diff --git a/params_shard_124.bin b/params_shard_124.bin new file mode 100644 index 0000000000000000000000000000000000000000..31b7f498bf25680477a9d9199e7e9e89674dcc72 --- /dev/null +++ b/params_shard_124.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3fa7cc4ee305451d3006c8fd456156c9cd0edd3038bd91246219a54671d3f1b +size 33554432 diff --git a/params_shard_126.bin b/params_shard_126.bin new file mode 100644 index 0000000000000000000000000000000000000000..df698ca942d7a4c16f176d1c94a3b3692fcdc960 --- /dev/null +++ b/params_shard_126.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f45b483752f9d5924f94b345c17d852e414d2f07c7d23f7878cfd4de366ee1c8 +size 29360128 diff --git a/params_shard_127.bin b/params_shard_127.bin new file mode 100644 index 0000000000000000000000000000000000000000..fae406ed56182a28c93c90464cde720153fcd4a7 --- /dev/null +++ b/params_shard_127.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010bdd2da86774f5bbe23f827be08a81a89d1e76d5b61d6562b13f4885a232ec +size 41943040 diff --git a/params_shard_128.bin b/params_shard_128.bin new file mode 100644 index 0000000000000000000000000000000000000000..99357832f3c9162de3231b5da6d8304f97560a1b --- /dev/null +++ b/params_shard_128.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6475928e324a6ea3c5cdc900e968133712feaba5e8d05656960d15c5c951119e +size 33554432 diff --git a/params_shard_129.bin b/params_shard_129.bin new file mode 100644 index 0000000000000000000000000000000000000000..8e3e32515be821c961f18291385541ec56847aa8 --- /dev/null +++ b/params_shard_129.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c26242c6d032e93715fe1dece76f53ca1ea6d786d22f34272d23faa5a99e90 +size 29376512 diff --git a/params_shard_13.bin b/params_shard_13.bin new file mode 100644 index 0000000000000000000000000000000000000000..2f1e5a920ee13eff22fe945e2acb8e81c19d1a41 --- /dev/null +++ b/params_shard_13.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:969949ecf1ad3a907302af570fe789b4a3436a2b1789751199070219e1ba735d +size 29392896 diff --git a/params_shard_132.bin b/params_shard_132.bin new file mode 100644 index 0000000000000000000000000000000000000000..273bc7a3210244b143b1693e21ac399120b1f9ca --- /dev/null +++ b/params_shard_132.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:189a66b0b11cf705c6677d133a1ddfaa12ed41eea674dd9d3dba9679babef382 +size 18923520 diff --git a/params_shard_134.bin b/params_shard_134.bin new file mode 100644 index 0000000000000000000000000000000000000000..ccaccb03b241c30a0ea68fdb1c6f2fb1beb38f04 --- /dev/null +++ b/params_shard_134.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07b90e1f15d12fff1b63c241c846de1bbc2317446a185351c0ee8322cd43fec9 +size 29360128 diff --git a/params_shard_135.bin b/params_shard_135.bin new file mode 100644 index 0000000000000000000000000000000000000000..585b9ee974facf5449c14c0225e7c1e26f9f4cd4 --- /dev/null +++ b/params_shard_135.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:844e8fa056e2d5492d15070c638f0366d8a9690846a9b2cf406f7a539bfc55c9 +size 41943040 diff --git a/params_shard_136.bin b/params_shard_136.bin new file mode 100644 index 0000000000000000000000000000000000000000..4da8d30734db929c5edaa68c0a65adfcae20af05 --- /dev/null +++ b/params_shard_136.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d95db84d1eb62e33ca935be6ad2167d1f5468cdf99426de58c37f4b09691d596 +size 33554432 diff --git a/params_shard_138.bin b/params_shard_138.bin new file mode 100644 index 0000000000000000000000000000000000000000..31f19c18481a62df951e1cbad4c8568c2a93e4f1 --- /dev/null +++ b/params_shard_138.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e48f4a7d59c1ad64779aafb5d6343356d9bc0c60b4f2be9363824439e431a53c +size 24150016 diff --git a/params_shard_140.bin b/params_shard_140.bin new file mode 100644 index 0000000000000000000000000000000000000000..331ac3e321368070df89febc987b1a8d3359b8a3 --- /dev/null +++ b/params_shard_140.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d9acce8edc013242fce71f3267244c197435b330d824e5e949fbf18d686bb2 +size 29360128 diff --git a/params_shard_141.bin b/params_shard_141.bin new file mode 100644 index 0000000000000000000000000000000000000000..545f390dd35f54a41fa0c03d44da31a5f8033e75 --- /dev/null +++ b/params_shard_141.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d89882226681016325722057810023594bf0d0a025333b369b3cdc7698b57204 +size 41943040 diff --git a/params_shard_142.bin b/params_shard_142.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0a3665935992078bd64138e75fc5fa4181b9bee --- /dev/null +++ b/params_shard_142.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98e3f6dca7e4c136a62c6b01edebef39c6314d44be749b6eed4a0bd1de2d9838 +size 33554432 diff --git a/params_shard_144.bin b/params_shard_144.bin new file mode 100644 index 0000000000000000000000000000000000000000..1bc1bbcc122321fc156fe4173a0beae4cd8542f8 --- /dev/null +++ b/params_shard_144.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8100f2c36e5e151760deb300a10c7b1f8c5d443a3ec7fc503feae9dd8c119460 +size 29360128 diff --git a/params_shard_145.bin b/params_shard_145.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c4f4a11a35aa0595e7ac5aa00eac216a7ca492d --- /dev/null +++ b/params_shard_145.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d74fa4d2d71fdb4dea5757a9c727a63dad0e88866e332b14c4a9c1ee82366ff +size 41943040 diff --git a/params_shard_146.bin b/params_shard_146.bin new file mode 100644 index 0000000000000000000000000000000000000000..4c2c6be63d98cc7f3dd23e0a1e7dad48dd9a8db2 --- /dev/null +++ b/params_shard_146.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a02e8b9a36371c3bd6650858b1a47492c3d488c1b1f8957b20b07e2fa6a209ff +size 33554432 diff --git a/params_shard_147.bin b/params_shard_147.bin new file mode 100644 index 0000000000000000000000000000000000000000..5e3a9d2ca639cd516257e31577ed612f00840913 --- /dev/null +++ b/params_shard_147.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1718641fffa40411c0fcb28dbda425cc7cd5c7c7f2fe5bf576ce7cd711bb2097 +size 29376512 diff --git a/params_shard_150.bin b/params_shard_150.bin new file mode 100644 index 0000000000000000000000000000000000000000..877e14add6803e553d5702e5a36e2992f5942e87 --- /dev/null +++ b/params_shard_150.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10604e88249efe5471637d9abe12c66d3168caeb3d16b0e147ec71fae7a8c2f3 +size 18923520 diff --git a/params_shard_152.bin b/params_shard_152.bin new file mode 100644 index 0000000000000000000000000000000000000000..0f2f9746463fd752afce568e3ec8fa3e871850bb --- /dev/null +++ b/params_shard_152.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fea641edf98b004256af5618ead377e79338a09371beaf6631098cf9527e3794 +size 29360128 diff --git a/params_shard_153.bin b/params_shard_153.bin new file mode 100644 index 0000000000000000000000000000000000000000..2887f3334c5a172efe9ec20534ae95f8dafbbeb3 --- /dev/null +++ b/params_shard_153.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79ce42348f441c68413899b0cc35f2f20c2c989347f733c6a2772acddbc34a61 +size 41943040 diff --git a/params_shard_154.bin b/params_shard_154.bin new file mode 100644 index 0000000000000000000000000000000000000000..cadcdfb7b0562ae8db3aafe9e149531cdf17959e --- /dev/null +++ b/params_shard_154.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebcc6706f7d324e1595bbee5e412d9f267c7904b6f1cc5bacc73339c81b89dc9 +size 33554432 diff --git a/params_shard_156.bin b/params_shard_156.bin new file mode 100644 index 0000000000000000000000000000000000000000..a2a17ef085d5daec4e7fc95539e01bb6a82255b3 --- /dev/null +++ b/params_shard_156.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5f42d6207a91ba1a5a4ddd7c06f4770fdf9abe16c165922f757c38c1575b14 +size 24150016 diff --git a/params_shard_158.bin b/params_shard_158.bin new file mode 100644 index 0000000000000000000000000000000000000000..837d4f7bd5757d8fc14ad10c104ef99df9f7be13 --- /dev/null +++ b/params_shard_158.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e8bced07c040543b332b25d1d561a5f0276ee6a50364abc8c36a0f72dff8a85 +size 29360128 diff --git a/params_shard_159.bin b/params_shard_159.bin new file mode 100644 index 0000000000000000000000000000000000000000..95d8b3363c0926fa82af96baf812e0f27e1c72a2 --- /dev/null +++ b/params_shard_159.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64990a8227268ecdaaa38769b2056630f8750c64632b6cd82b86b1ae1964a40c +size 41943040 diff --git a/params_shard_16.bin b/params_shard_16.bin new file mode 100644 index 0000000000000000000000000000000000000000..ec4b30922024e07c704ddad3263f120a6643182c --- /dev/null +++ b/params_shard_16.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0daab0efb1d13a3e1b23dbc8105f63c9be7d02de0c4ffe448dcdf6a1914ca041 +size 18923520 diff --git a/params_shard_160.bin b/params_shard_160.bin new file mode 100644 index 0000000000000000000000000000000000000000..a1476d69c6376545496331ab8b69f8dbfe94ae20 --- /dev/null +++ b/params_shard_160.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:666f70970e4e1b9d5ee05c092f02ffbf1bcf508301f5f937992d442c2dc4d25b +size 33554432 diff --git a/params_shard_161.bin b/params_shard_161.bin new file mode 100644 index 0000000000000000000000000000000000000000..b3100fa70b902de3e087902755ba91d467d33c98 --- /dev/null +++ b/params_shard_161.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40b9cbf08535a079adee32da3712888edb2d36a2fc199b34ecc26201ea49daee +size 41943040 diff --git a/params_shard_162.bin b/params_shard_162.bin new file mode 100644 index 0000000000000000000000000000000000000000..13df5bf7a2c504a16ff3128539c054af2c1ab663 --- /dev/null +++ b/params_shard_162.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e893319acab2c6fadfd26ceff650eb5fa6fb38cb9a7e832892403be76454c1fe +size 33554432 diff --git a/params_shard_163.bin b/params_shard_163.bin new file mode 100644 index 0000000000000000000000000000000000000000..fff4c6d1bfd6f2a8a43e76e07b3a1d3982837b4a --- /dev/null +++ b/params_shard_163.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef3dc90ea4b64a6c52a4cec831859ec9d17717c34b809cae4f1908c9572db10d +size 29376512 diff --git a/params_shard_166.bin b/params_shard_166.bin new file mode 100644 index 0000000000000000000000000000000000000000..91ef6701694a16e3de0c44110fd7f4c5bcdb0044 --- /dev/null +++ b/params_shard_166.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3975da25c2841b02587232c56a49816aa1e95c693a51ce268be1979aa4d2c1c +size 29360128 diff --git a/params_shard_168.bin b/params_shard_168.bin new file mode 100644 index 0000000000000000000000000000000000000000..4fc89f4a259128c5c575419751b3166605fa2f5e --- /dev/null +++ b/params_shard_168.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12fbde893b9711bffdffa489de817a85f74478059cfb9a2ff59d4f823c28eb1c +size 18923520 diff --git a/params_shard_170.bin b/params_shard_170.bin new file mode 100644 index 0000000000000000000000000000000000000000..8832f63e5b3a5efed82db021a58541cb9a607719 --- /dev/null +++ b/params_shard_170.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30f5ef3b29cb6e75d89336be8d04e7f40ececc781fc9426ca3559d94cf93a609 +size 29360128 diff --git a/params_shard_171.bin b/params_shard_171.bin new file mode 100644 index 0000000000000000000000000000000000000000..713753a1d542700d3ee058c1586dd463d8524112 --- /dev/null +++ b/params_shard_171.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e46477618a2b0cd5cfe1f0cfddc48310a964901b16430b6154a6bdbffc8697c +size 41943040 diff --git a/params_shard_172.bin b/params_shard_172.bin new file mode 100644 index 0000000000000000000000000000000000000000..e85c9e9a72071080657e53ae5885ef1fe4a25786 --- /dev/null +++ b/params_shard_172.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a984f807b1206d6602839075d5735d0e3b36d2e962fe5c29ba05722601aa14e4 +size 33554432 diff --git a/params_shard_174.bin b/params_shard_174.bin new file mode 100644 index 0000000000000000000000000000000000000000..8108670fe0883341bd8ab443e82337671e6f7773 --- /dev/null +++ b/params_shard_174.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e2d76e4be7bdc7937a7b405ab362cc81c2337b0f9d1ed8c73d7c28f1bbc887 +size 24150016 diff --git a/params_shard_176.bin b/params_shard_176.bin new file mode 100644 index 0000000000000000000000000000000000000000..3e78f3c14a5f4d2ef93c3c1721f34ec400d4c055 --- /dev/null +++ b/params_shard_176.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a89367a064f7a2f0cffe4d746be22f79d364ce4befefb60dff403b6dce68330d +size 29360128 diff --git a/params_shard_178.bin b/params_shard_178.bin new file mode 100644 index 0000000000000000000000000000000000000000..cb80751f0565725e40d55da22dce46e8230d8e8d --- /dev/null +++ b/params_shard_178.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f61c0c5c90b189a50f085005ae167d453b1e199751358eaefb5ac5a88c0cb89 +size 33554432 diff --git a/params_shard_18.bin b/params_shard_18.bin new file mode 100644 index 0000000000000000000000000000000000000000..f709bb1b4b594bad72ce3a8780c26dcfc5e376cf --- /dev/null +++ b/params_shard_18.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d82780f52daf63ef98e70e13f7f430f042110a143a3edbc866cdf91e0225407d +size 29360128 diff --git a/params_shard_181.bin b/params_shard_181.bin new file mode 100644 index 0000000000000000000000000000000000000000..e3c8ceb0a0aa6160d5ccfe7dfd89cb762464d543 --- /dev/null +++ b/params_shard_181.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:807e64e2612257f4969c2a4e519dbace52c1d5d5735dcdea06782b89b648393b +size 29392896 diff --git a/params_shard_183.bin b/params_shard_183.bin new file mode 100644 index 0000000000000000000000000000000000000000..d45d80ba5ee2a5781e3e1bd68680ea31e04a66ef --- /dev/null +++ b/params_shard_183.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f10cde5abcdf382371a6ed92b3c872e3878ad8eb74314ec6af0a4c6cac5b3d +size 29360128 diff --git a/params_shard_184.bin b/params_shard_184.bin new file mode 100644 index 0000000000000000000000000000000000000000..f2e82ca9b7c9fc1da4dd25f6ae89106381dfb745 --- /dev/null +++ b/params_shard_184.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2a99012c7217c32dffb6480cd618a253db6eeae1c7acbb53e7f4ba137b6c68d +size 33554432 diff --git a/params_shard_186.bin b/params_shard_186.bin new file mode 100644 index 0000000000000000000000000000000000000000..9ce6ee55f2c25928db65d0d9aca25c9443de3c27 --- /dev/null +++ b/params_shard_186.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c150f6f412024783907b8d9c56afc2a3175155448b0947f03d9c0438c3faabcd +size 18907136 diff --git a/params_shard_188.bin b/params_shard_188.bin new file mode 100644 index 0000000000000000000000000000000000000000..52758cee05c971578650c43808606934e0d221cc --- /dev/null +++ b/params_shard_188.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:684091d7226b7035211f0816137f278d831b802ca9c821ce40354286125da011 +size 29360128 diff --git a/params_shard_189.bin b/params_shard_189.bin new file mode 100644 index 0000000000000000000000000000000000000000..04e58e42722cff51d7c63645ac1a71a6f52b08d1 --- /dev/null +++ b/params_shard_189.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e99b60ba9c67ea56898ff078711359a77b6e36793f42568ba2a4b5375fe9005 +size 41943040 diff --git a/params_shard_19.bin b/params_shard_19.bin new file mode 100644 index 0000000000000000000000000000000000000000..28fcd1dce8e89a70a605d3e9b2a46feb8fcaccb7 --- /dev/null +++ b/params_shard_19.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:821e1d752819c63d8d9d8fde0cd9d0cdc582625965c71c451489e24b1dc60c52 +size 41943040 diff --git a/params_shard_190.bin b/params_shard_190.bin new file mode 100644 index 0000000000000000000000000000000000000000..7a4567596d1092ba059740b3f988fb835d16d636 --- /dev/null +++ b/params_shard_190.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac70964a2025775a6ea51348cd34b4c385957be9a8cd31c33b94167d321e1430 +size 33554432 diff --git a/params_shard_192.bin b/params_shard_192.bin new file mode 100644 index 0000000000000000000000000000000000000000..a484e24eb17f7e9ac8403f777f032ec6ad06cca6 --- /dev/null +++ b/params_shard_192.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9b0cc3a3f7ece8089816f22a87447b282aeeeb19bd53f37d465c505fd6eb4af +size 24150016 diff --git a/params_shard_194.bin b/params_shard_194.bin new file mode 100644 index 0000000000000000000000000000000000000000..531b65bd8a5dc188386c2d121c545877a9cf0e1c --- /dev/null +++ b/params_shard_194.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bdf4f6574afb5681ab90621c96de205ed30c5637d0c818f4eb9051da70888ab +size 29360128 diff --git a/params_shard_195.bin b/params_shard_195.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1824d2b6fcecc4fa3d25ec709a50b7f4edbe6c4 --- /dev/null +++ b/params_shard_195.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d8bc420268f81d9f74b86d30f4daff43e3b2c68a9d5449ac3e46aefd8331864 +size 41943040 diff --git a/params_shard_196.bin b/params_shard_196.bin new file mode 100644 index 0000000000000000000000000000000000000000..795daddf9dc2169e8337256442a5f9f1b6345787 --- /dev/null +++ b/params_shard_196.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78777ab6fb601fad493852812773d6a8f57830e403d75283703bff6911e7e68f +size 33554432 diff --git a/params_shard_198.bin b/params_shard_198.bin new file mode 100644 index 0000000000000000000000000000000000000000..b8be2a2bd312bb91ff08c9fc643ade24fdcb92c3 --- /dev/null +++ b/params_shard_198.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:418016777c3ebeb3b2cb817891b4692494e3aeceed4e086fdb647955934363b5 +size 24150016 diff --git a/params_shard_20.bin b/params_shard_20.bin new file mode 100644 index 0000000000000000000000000000000000000000..b21ee7d0f0ffcfa4dbe4ddc63d900f997dcd298b --- /dev/null +++ b/params_shard_20.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:875dc6c3078e04100ac347331db368440a0c7f893319da83ede300ae788a846c +size 33554432 diff --git a/params_shard_200.bin b/params_shard_200.bin new file mode 100644 index 0000000000000000000000000000000000000000..b6b50655a73ae32bd5a4137dae8bc55806c73192 --- /dev/null +++ b/params_shard_200.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8096031effee58205bea76a40bbf8262670a0e8a546a8d20b8ef9bd27d8bad75 +size 29360128 diff --git a/params_shard_201.bin b/params_shard_201.bin new file mode 100644 index 0000000000000000000000000000000000000000..a96814806f0be642ee90d6e90fa0262e7a01df5c --- /dev/null +++ b/params_shard_201.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc37eabde223d40c436da21e7179e66ac08ebd7618cf29accd795d8d843d4db +size 41943040 diff --git a/params_shard_202.bin b/params_shard_202.bin new file mode 100644 index 0000000000000000000000000000000000000000..cd5004ce3641d019c20b977ae3ba9adecc4d4444 --- /dev/null +++ b/params_shard_202.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24b52cc672a77cad3b92adb2e0b8634b934fa3080e01031549e54ddde9351494 +size 33554432 diff --git a/params_shard_204.bin b/params_shard_204.bin new file mode 100644 index 0000000000000000000000000000000000000000..5b9652af9bb5fbfb91418ff2a0f452c9236b5fdb --- /dev/null +++ b/params_shard_204.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5997e59634a2ef702695a70d702cf87d87e0ec38e406c3fef2b95a107374d2e +size 24150016 diff --git a/params_shard_206.bin b/params_shard_206.bin new file mode 100644 index 0000000000000000000000000000000000000000..4181fcd97cbbc80de78faac4520af9119caa0dd0 --- /dev/null +++ b/params_shard_206.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d468aaed213f2cf4eecfcc71d1ac0555c48da757bc9f7769199146cc775680ef +size 29360128 diff --git a/params_shard_207.bin b/params_shard_207.bin new file mode 100644 index 0000000000000000000000000000000000000000..f5ba83428c48363ab62f1ed0801c61f61c239aa4 --- /dev/null +++ b/params_shard_207.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b9b8bce2a14d7ddf67f7bbb351fb392be1631bf8b1c19d597b53b6f23e21c5c +size 41943040 diff --git a/params_shard_208.bin b/params_shard_208.bin new file mode 100644 index 0000000000000000000000000000000000000000..37a65923f5d514740f981034e369bcbbae36922f --- /dev/null +++ b/params_shard_208.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6077c95dabf962e60c418953b47879e9adecc3b994ef6c6c5e67ab4b0410c4c0 +size 33554432 diff --git a/params_shard_210.bin b/params_shard_210.bin new file mode 100644 index 0000000000000000000000000000000000000000..3b681178709aaeff9550077749ce5eef351c9464 --- /dev/null +++ b/params_shard_210.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e627c10444486a7e76479d331613e80f9df22ccb9759dd485b1136d83c5b827 +size 29360128 diff --git a/params_shard_212.bin b/params_shard_212.bin new file mode 100644 index 0000000000000000000000000000000000000000..696f70884d89e60d5da0dbaebe7229a226933dd1 --- /dev/null +++ b/params_shard_212.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb80e0037cbbd30b73de91ea7771ce06802ca759c20ae3edd12d7ae8427f73cb +size 33554432 diff --git a/params_shard_213.bin b/params_shard_213.bin new file mode 100644 index 0000000000000000000000000000000000000000..e01fc80a3f5a57b0dd78190c50969aa61d13afa8 --- /dev/null +++ b/params_shard_213.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ad66bc56d83d175133e3357031c16045a05ef4c42de3419391ec4c50363e7e7 +size 29376512 diff --git a/params_shard_216.bin b/params_shard_216.bin new file mode 100644 index 0000000000000000000000000000000000000000..8c8793e4dde560613869f42ac3ab5e290cf3a796 --- /dev/null +++ b/params_shard_216.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:142d9c3f88150e16b9897cd3b483d850fc803d0075a896847b0741d39a66011e +size 29360128 diff --git a/params_shard_218.bin b/params_shard_218.bin new file mode 100644 index 0000000000000000000000000000000000000000..e94c1e11f4c11fdd74820bae3af5cdef2c00b70f --- /dev/null +++ b/params_shard_218.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51331019c05383dcce18a52257a9d5bb7abafba3702f0bd5489faba6aba38325 +size 18923520 diff --git a/params_shard_22.bin b/params_shard_22.bin new file mode 100644 index 0000000000000000000000000000000000000000..d4e05768f2e8baa0bf5fe45a6752703d29606d29 --- /dev/null +++ b/params_shard_22.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:949b8647acdc44378528ce1b7390133388e7635a95905ab84102dfa17fe5cb22 +size 24150016 diff --git a/params_shard_220.bin b/params_shard_220.bin new file mode 100644 index 0000000000000000000000000000000000000000..4d717db3975c52526f1e89a3b5b0922bf480c39f --- /dev/null +++ b/params_shard_220.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75eb786f1f5b39908ebf358aeff6c40ef6921ff71c4ac483f859515c7a0a1efb +size 29360128 diff --git a/params_shard_222.bin b/params_shard_222.bin new file mode 100644 index 0000000000000000000000000000000000000000..7c475a933d107b0d90a6a1dc64eb16d6fbe18069 --- /dev/null +++ b/params_shard_222.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee6e7f86280dfe02499990b9df57dbd14c2de18112dcaa9138eb7d04c40e294 +size 33554432 diff --git a/params_shard_224.bin b/params_shard_224.bin new file mode 100644 index 0000000000000000000000000000000000000000..d1018e3b1172f75e6fa84f5c2cee653d5bb82923 --- /dev/null +++ b/params_shard_224.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ded6a9dbc52f76459182e3721f4cfb71e7444ef0433139b1d9c960a4b19fa7 +size 24150016 diff --git a/params_shard_226.bin b/params_shard_226.bin new file mode 100644 index 0000000000000000000000000000000000000000..79c8ba69bcf3285462fc78933ce197937b158206 --- /dev/null +++ b/params_shard_226.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c95aabdd6f462bb7ea194090f5389039785d269938662484dab56be034ea26f +size 29360128 diff --git a/params_shard_234.bin b/params_shard_234.bin new file mode 100644 index 0000000000000000000000000000000000000000..2119f981489a07819e43ec578c65d7276ec5bef3 --- /dev/null +++ b/params_shard_234.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d76ec3434c020d7aa63085bc7531a26568baa435edd0ed1aa7f328a92b2cae21 +size 29360128 diff --git a/params_shard_236.bin b/params_shard_236.bin new file mode 100644 index 0000000000000000000000000000000000000000..f1a4826d8834ff661f6d06611da29adc989900e2 --- /dev/null +++ b/params_shard_236.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9118eb752848705a56a80e84334a9fee0c2765aa091d3d493c762c71279a6de8 +size 29409280 diff --git a/params_shard_243.bin b/params_shard_243.bin new file mode 100644 index 0000000000000000000000000000000000000000..6508e6cc6cd96fbe057c2aea501723e8f18c64bc --- /dev/null +++ b/params_shard_243.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fd71ffb834d1d1829b5855c7dae471ac37b3764895512d0b0bd07724d99c27f +size 29392896 diff --git a/params_shard_245.bin b/params_shard_245.bin new file mode 100644 index 0000000000000000000000000000000000000000..9a5e25fd58d52f393c09c89e977fd3210e8867a6 --- /dev/null +++ b/params_shard_245.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50539e4c8860760954c70151b85b9a73171534992b457f59e6595ed435a9a3ea +size 29360128 diff --git a/params_shard_25.bin b/params_shard_25.bin new file mode 100644 index 0000000000000000000000000000000000000000..0671949b202193abd0b8b51802ffbfaa29c5e171 --- /dev/null +++ b/params_shard_25.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e795aec6ea4de0adb40d4f79a1dcae9d4088e30028d83eb549b29428f0ffd2 +size 41943040 diff --git a/params_shard_250.bin b/params_shard_250.bin new file mode 100644 index 0000000000000000000000000000000000000000..012dc4785637ceee4667b66c1b3af14b23af5398 --- /dev/null +++ b/params_shard_250.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80a4fb1a644d6fe44835bb59a30033051af5c78df1e67c90f5d18a2573851cd7 +size 28360704 diff --git a/params_shard_252.bin b/params_shard_252.bin new file mode 100644 index 0000000000000000000000000000000000000000..143432d782e45f8f40682fd01f02bbf2cc2030f9 --- /dev/null +++ b/params_shard_252.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:109913d98d1da28bc81a15f9121c28b9096cf07e27c7774174e942d8825e5eba +size 29360128 diff --git a/params_shard_26.bin b/params_shard_26.bin new file mode 100644 index 0000000000000000000000000000000000000000..482ffa727649ddac4d5010ec09d2aefb662129e1 --- /dev/null +++ b/params_shard_26.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf38b74344db63c899ca65f4380800b77196534d17fcd3f22a80d594a41d4e4e +size 33554432 diff --git a/params_shard_27.bin b/params_shard_27.bin new file mode 100644 index 0000000000000000000000000000000000000000..07052aea39ca80460711817bfe22f27cda3c6433 --- /dev/null +++ b/params_shard_27.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:adbf3bc4938b890e5dac4d8b3ba0b6874cac7ff99ec62341302e53c43991bb4d +size 41943040 diff --git a/params_shard_28.bin b/params_shard_28.bin new file mode 100644 index 0000000000000000000000000000000000000000..72d25e178aeb2817e7cd4b44439d5588a57f2958 --- /dev/null +++ b/params_shard_28.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50a79c9bad02464d9dd1d6980f4898ffb799ee867a2bd7145c7c02ed41d6f09b +size 33554432 diff --git a/params_shard_29.bin b/params_shard_29.bin new file mode 100644 index 0000000000000000000000000000000000000000..f821fc95492a4e5ee807636029da97d8b973f17f --- /dev/null +++ b/params_shard_29.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fde0652a8f750284673ed1fa6c3610a27980ccaf6004a1a437a8684fc087cfdd +size 29376512 diff --git a/params_shard_32.bin b/params_shard_32.bin new file mode 100644 index 0000000000000000000000000000000000000000..c470d6288b7f658a6736f15c1e8420cb6ada1ac0 --- /dev/null +++ b/params_shard_32.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97ce555d42b7061c3e8c56c78e3bdb25e61c950adcac49c897afdf2bb57a3288 +size 29360128 diff --git a/params_shard_33.bin b/params_shard_33.bin new file mode 100644 index 0000000000000000000000000000000000000000..60fc7aeb2402440694fac5fbb5c5d0af20177536 --- /dev/null +++ b/params_shard_33.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b5ab831e06a1453da823911c5947708df9da4cf21ed968cc64444d06f17e66d +size 41943040 diff --git a/params_shard_34.bin b/params_shard_34.bin new file mode 100644 index 0000000000000000000000000000000000000000..a51f926670f70d3d749462c94f0acf0895f44aea --- /dev/null +++ b/params_shard_34.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9fedc0be2b380dca4602fc08af4c229a524e6e19f8b8a2ff9bca1f4b5e0d10a +size 33554432 diff --git a/params_shard_36.bin b/params_shard_36.bin new file mode 100644 index 0000000000000000000000000000000000000000..00faea10ff294ae90e7af3362e87785a68806332 --- /dev/null +++ b/params_shard_36.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fc9773be55e4b9d7a61f3030f6dbb1cf7401e5067ed2c187f38cf47b1c41c55 +size 28360704 diff --git a/params_shard_38.bin b/params_shard_38.bin new file mode 100644 index 0000000000000000000000000000000000000000..28d3700e5fe8fc695b32f2fb667af75b5a47e0f5 --- /dev/null +++ b/params_shard_38.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22c4accebdc36e6985f28cc0cc76aa0903b4500eb21869110317cda2b17a437 +size 29360128 diff --git a/params_shard_39.bin b/params_shard_39.bin new file mode 100644 index 0000000000000000000000000000000000000000..260eb0af5c9370071e4ea8241eefbb12f215449d --- /dev/null +++ b/params_shard_39.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61988b41064a25d1aff73019813d2059abbd148493d8d687fd53fabb23879f37 +size 41943040 diff --git a/params_shard_40.bin b/params_shard_40.bin new file mode 100644 index 0000000000000000000000000000000000000000..54fd45e5a7bd7262407145ab4be047ca58a11ec6 --- /dev/null +++ b/params_shard_40.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:074a43aa3d69a51eb7fdb0dcc695c4e456aa58b879e0a32e82573fce70f7c7f5 +size 33554432 diff --git a/params_shard_42.bin b/params_shard_42.bin new file mode 100644 index 0000000000000000000000000000000000000000..9f9261fbd56dac871c0209fdf2280ae761225914 --- /dev/null +++ b/params_shard_42.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:216f8b3090489f4bf91d026ffa69a5607e627fd1c698b77aaffe694dd92650e1 +size 29360128 diff --git a/params_shard_43.bin b/params_shard_43.bin new file mode 100644 index 0000000000000000000000000000000000000000..c76f4190178aecf9838ff83b0d72665f3b62d721 --- /dev/null +++ b/params_shard_43.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd6c9336c13962ca5a6cd0539f438ec4ba040af61a76e7a934f92d0f4990dd2 +size 41943040 diff --git a/params_shard_44.bin b/params_shard_44.bin new file mode 100644 index 0000000000000000000000000000000000000000..1b45ad01b576e0c2ad8e96abc71b795bbf1145a7 --- /dev/null +++ b/params_shard_44.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:898f0de8c897a6dea488bf118d0f1d9dd985b441bce5e25a255d9d344453c563 +size 33554432 diff --git a/params_shard_45.bin b/params_shard_45.bin new file mode 100644 index 0000000000000000000000000000000000000000..7cf4bc5a36aa520f2be45a74bbda75330c64e6d6 --- /dev/null +++ b/params_shard_45.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a85ebc0b3c5d73cb14aab3ee1f3320604711448d212c2684ccb7008040a7443 +size 29376512 diff --git a/params_shard_48.bin b/params_shard_48.bin new file mode 100644 index 0000000000000000000000000000000000000000..9434c80497c662762b4607bd043662bc9f88fce7 --- /dev/null +++ b/params_shard_48.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dca809d583a256770b79e8bd01ae16eb1a00ebd97098262257494aa7ad4943b0 +size 18923520 diff --git a/params_shard_50.bin b/params_shard_50.bin new file mode 100644 index 0000000000000000000000000000000000000000..9f21eefa9bca1a4a8c94bb73204bf94ad42ef71e --- /dev/null +++ b/params_shard_50.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9ab507b6df41a288aa3f6e8ce769fe2775e2bc35a1e2f999e9c67fcf2b690fe +size 29360128 diff --git a/params_shard_51.bin b/params_shard_51.bin new file mode 100644 index 0000000000000000000000000000000000000000..796853d59a691f200011853ffb97307515c8bad8 --- /dev/null +++ b/params_shard_51.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e595cd32da5b42fbfa4452378995f7c6d8166818d65c87e067f1e1197709d3a +size 41943040 diff --git a/params_shard_52.bin b/params_shard_52.bin new file mode 100644 index 0000000000000000000000000000000000000000..c35a484a6cffbc1573c070877f56fedba817d239 --- /dev/null +++ b/params_shard_52.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7d03a42a50a6deba30d86c178f2f762a6827def0758f905b9f8b64419abd637 +size 33554432 diff --git a/params_shard_54.bin b/params_shard_54.bin new file mode 100644 index 0000000000000000000000000000000000000000..a00726d826f8e5758f39c275ed18ca4e93a4da37 --- /dev/null +++ b/params_shard_54.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f75a64f1928d19678c7d910db470d27814f83acdd22b6857ab5a23c87c858e3c +size 24150016 diff --git a/params_shard_56.bin b/params_shard_56.bin new file mode 100644 index 0000000000000000000000000000000000000000..35c1a168f4e6d97e90b2045d5c3b54b59aaafdfb --- /dev/null +++ b/params_shard_56.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae698b9b726b21642ff275893b0b46c525cab4e4b97d616af6f381e04f282e56 +size 29360128 diff --git a/params_shard_57.bin b/params_shard_57.bin new file mode 100644 index 0000000000000000000000000000000000000000..d0b84d98a78e56fd82f425908c62ddc32de74992 --- /dev/null +++ b/params_shard_57.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d75c25015fada6b68216636660d25a83d761674469b3922475ef0e44293f6dc +size 41943040 diff --git a/params_shard_58.bin b/params_shard_58.bin new file mode 100644 index 0000000000000000000000000000000000000000..a15425a037b9aaf3c110c31f0b50b66c5fc0bae0 --- /dev/null +++ b/params_shard_58.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d209546332bfb563a81d044b06bbf5029b2c96a0c1de8ceb4517c016da0fada +size 33554432 diff --git a/params_shard_6.bin b/params_shard_6.bin new file mode 100644 index 0000000000000000000000000000000000000000..9d86e23c66e89ce05bc2021a580f35d439ab622a --- /dev/null +++ b/params_shard_6.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c0db56df1e554092af0d34fea10c3ce21be69cf99557ce4e0e9d1368f076555 +size 29360128 diff --git a/params_shard_60.bin b/params_shard_60.bin new file mode 100644 index 0000000000000000000000000000000000000000..5a36dfaa5630896976503a235d54d6df3227ace3 --- /dev/null +++ b/params_shard_60.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad5becd34a1a22e26356c6fa991784a161d3942b4a3912ac9ed6d876ae28aa17 +size 29360128 diff --git a/params_shard_61.bin b/params_shard_61.bin new file mode 100644 index 0000000000000000000000000000000000000000..02fa58cc3c96d16192b63c8944c79e4a1cd77ae5 --- /dev/null +++ b/params_shard_61.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52ba79d66480e23fe297cc4ec6f42902960813605af1430a5633874662143f82 +size 41943040 diff --git a/params_shard_62.bin b/params_shard_62.bin new file mode 100644 index 0000000000000000000000000000000000000000..457b0367abbe90353e921251e530ab04bdccf3df --- /dev/null +++ b/params_shard_62.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c2c1c92738b0100f07a1facfba4521e3b62223376833f9a806e9fc5f04988e8 +size 33554432 diff --git a/params_shard_63.bin b/params_shard_63.bin new file mode 100644 index 0000000000000000000000000000000000000000..433342ef2c801c62ca9cf92385610b9eb0e10289 --- /dev/null +++ b/params_shard_63.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d899b5a1a49f6402b81a507f686e7e02bb4ce9d81bc37faf4f6497e2315c40e0 +size 29376512 diff --git a/params_shard_66.bin b/params_shard_66.bin new file mode 100644 index 0000000000000000000000000000000000000000..3c93c860b55d3fe8884e7de5d02e2be376174ac9 --- /dev/null +++ b/params_shard_66.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:305f75833c4093b6f2382440af504454bb18f1d319ce976f020d4a42ce0aaf9a +size 18923520 diff --git a/params_shard_68.bin b/params_shard_68.bin new file mode 100644 index 0000000000000000000000000000000000000000..edbf723e777ea991fd072a698d2b43d7e1fca3b2 --- /dev/null +++ b/params_shard_68.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dbd08ad6b7d58c6c963c25d8cbec6dd01d515706e26e73cbebc9be74bec0b95 +size 29360128 diff --git a/params_shard_7.bin b/params_shard_7.bin new file mode 100644 index 0000000000000000000000000000000000000000..f2428ed4bc09444c2748deaeb8c295c527db127a --- /dev/null +++ b/params_shard_7.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd41e926043623948adb0deaddbc7878bb30574540455eaeb903adb6561bd78f +size 41943040 diff --git a/params_shard_70.bin b/params_shard_70.bin new file mode 100644 index 0000000000000000000000000000000000000000..a1541fbac36659fde22ff601f0dff62f52f38bcf --- /dev/null +++ b/params_shard_70.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa3f624e9d84f188ff7b24fac0f75559719b9480fc023088c1e4b32671508d2c +size 33554432 diff --git a/params_shard_72.bin b/params_shard_72.bin new file mode 100644 index 0000000000000000000000000000000000000000..086d18b67e02f1cfaaad4a88d5a47dd880b13dbf --- /dev/null +++ b/params_shard_72.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52d91737c55ca13a1193cad8eb116669fa06c7ab9572eea4d5ea62f6dd16a02a +size 24150016 diff --git a/params_shard_74.bin b/params_shard_74.bin new file mode 100644 index 0000000000000000000000000000000000000000..3a22d586071f1fbfd9226c26aaee625b2f984163 --- /dev/null +++ b/params_shard_74.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3205b2bfd845f0df212ef4b42da25d049dc67a8adf1d44d86b1c65c6b94d3df0 +size 29360128 diff --git a/params_shard_75.bin b/params_shard_75.bin new file mode 100644 index 0000000000000000000000000000000000000000..7d48c10697679efefcb3ec69415a92d16048b44c --- /dev/null +++ b/params_shard_75.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e9516641d530f484267ceeff5523748a6f44e11745cdc1224c9a3383638d812 +size 41943040 diff --git a/params_shard_76.bin b/params_shard_76.bin new file mode 100644 index 0000000000000000000000000000000000000000..803dd86787882ea742b3691dba42d1885fe2cd74 --- /dev/null +++ b/params_shard_76.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d53c009a0989e59e228c22137b66102475b9c3aaf71de82ec603b305e46acbca +size 33554432 diff --git a/params_shard_77.bin b/params_shard_77.bin new file mode 100644 index 0000000000000000000000000000000000000000..008eea06a3ab403d9d46fc8d636429f39ab6913f --- /dev/null +++ b/params_shard_77.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3e95d29a3a3fa730afee8e7168cf980748a7c1c6e0701cb2fee5a53123ee11 +size 41943040 diff --git a/params_shard_78.bin b/params_shard_78.bin new file mode 100644 index 0000000000000000000000000000000000000000..531ef0958d4f283e30bd41e5ad29ef7ef9ac467a --- /dev/null +++ b/params_shard_78.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:853d90df2bfc14960bc1777e8b83b04b2603246f48d16000b8cf1c6d03ffb19d +size 33554432 diff --git a/params_shard_79.bin b/params_shard_79.bin new file mode 100644 index 0000000000000000000000000000000000000000..d52d7a58dc5f6ad2d51bbf698db7b94f6b20e0b0 --- /dev/null +++ b/params_shard_79.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf367e38193cbc486820ff33fd62fa38109b4766f7d8a7a21c33b50663f63195 +size 29376512 diff --git a/params_shard_8.bin b/params_shard_8.bin new file mode 100644 index 0000000000000000000000000000000000000000..b6f4e5698146403fe1c16312d102185a74a25e89 --- /dev/null +++ b/params_shard_8.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d5cc4583bbd81d3b2bf68281556908145ceeaf57c592456470e24c907a8570e +size 33554432 diff --git a/params_shard_82.bin b/params_shard_82.bin new file mode 100644 index 0000000000000000000000000000000000000000..b31ee11bba76b40edf1e5588a938dfcb5a83ff99 --- /dev/null +++ b/params_shard_82.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d168aaf6c901365f4f24b1c7c853319673daec0df93b673f5bcf3d8063d7289e +size 29360128 diff --git a/params_shard_84.bin b/params_shard_84.bin new file mode 100644 index 0000000000000000000000000000000000000000..4fff9daba20dea7ee6a0d596fa7b349d7c14fd87 --- /dev/null +++ b/params_shard_84.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21a4ca9215f85552864b72b17eed2416b181b7bb493f45981e2c5fb74746a3c3 +size 18923520 diff --git a/params_shard_86.bin b/params_shard_86.bin new file mode 100644 index 0000000000000000000000000000000000000000..bfb38ac7ed63d882c4dd48f38967b15b567e9189 --- /dev/null +++ b/params_shard_86.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:238431bda9889f35f66eb1a9abf05979d223ed835c5b802007b351272443b82f +size 29360128 diff --git a/params_shard_87.bin b/params_shard_87.bin new file mode 100644 index 0000000000000000000000000000000000000000..27ce7ed2c5bec08bc6e3302087b2eb28362e9514 --- /dev/null +++ b/params_shard_87.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:086f15f6e07d39c08abe45ae41d40219c15027a5fe039446233084b087d68b59 +size 41943040 diff --git a/params_shard_88.bin b/params_shard_88.bin new file mode 100644 index 0000000000000000000000000000000000000000..ec84129cdbf3919c4620b4392f2777e23c7ce9f3 --- /dev/null +++ b/params_shard_88.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:711ec61fc14685e45101dd33c1929020151e5835811ec229a6af114b030d6e76 +size 33554432 diff --git a/params_shard_90.bin b/params_shard_90.bin new file mode 100644 index 0000000000000000000000000000000000000000..bfbe282235d5b8d87b1676814fbd7d202a7829ab --- /dev/null +++ b/params_shard_90.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a97974882901e620de1525e12f6433b5c623849703c303dab3e8117a53cc131 +size 24150016 diff --git a/params_shard_92.bin b/params_shard_92.bin new file mode 100644 index 0000000000000000000000000000000000000000..a4c28225acf2a5562b5cbdf8cc10fa089478fa3b --- /dev/null +++ b/params_shard_92.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaf24bb74a956bb160240be9eaebb55922168f83d0e2a4b96d319ffd46c1261d +size 29360128 diff --git a/params_shard_93.bin b/params_shard_93.bin new file mode 100644 index 0000000000000000000000000000000000000000..365beaf35d16f2e48feded9b51ac033a85e2c64b --- /dev/null +++ b/params_shard_93.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c3a51a42741aa5728574a388376793f3eea8cde5bcef9883eee522ffa1f94b7 +size 41943040 diff --git a/params_shard_94.bin b/params_shard_94.bin new file mode 100644 index 0000000000000000000000000000000000000000..04a11219ee6fe3b72a296e9a99ae99501897c9ea --- /dev/null +++ b/params_shard_94.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dddb0c40feea18f0140049e8a7e0bb4d62468eeb91ea10db0dd649b7a7453d17 +size 33554432 diff --git a/params_shard_95.bin b/params_shard_95.bin new file mode 100644 index 0000000000000000000000000000000000000000..cd01870a546af4f700c89ed5381a3ddc74b24e4b --- /dev/null +++ b/params_shard_95.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84d4ad3f8b17bed9fe5fde1ca6f3bcbbd010e2f4bb0c9596f5b6dbdeeb9c448d +size 41943040 diff --git a/params_shard_97.bin b/params_shard_97.bin new file mode 100644 index 0000000000000000000000000000000000000000..f238db76db0a004ebb990154b2c056780278dae7 --- /dev/null +++ b/params_shard_97.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02860b6b36dec5501ef8606edb5c99f665a4b6bf4657622452f8f5f3e5610faf +size 29392896 diff --git a/params_shard_99.bin b/params_shard_99.bin new file mode 100644 index 0000000000000000000000000000000000000000..0f13c14a3602a71bb6f9cc306d37dd605a0024c0 --- /dev/null +++ b/params_shard_99.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:134148e6285edae214df80329ce161922f1c26795c80fe9beb7869695588cdd6 +size 29360128 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..41cd8d1ca52c3fc5feaf8445ca922b27f8e8ea8b --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2064 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|finetune_right_pad_id|>", + "tokenizer_class": "PreTrainedTokenizerFast" +}