| { | |
| "metadata": { | |
| "ParamSize": 170, | |
| "ParamBytes": 988065536.0, | |
| "BitsPerParam": 16.0 | |
| }, | |
| "records": [ | |
| { | |
| "dataPath": "params_shard_0.bin", | |
| "format": "raw-shard", | |
| "nbytes": 272269312, | |
| "records": [ | |
| { | |
| "name": "model.embed_tokens.weight", | |
| "shape": [ | |
| 151936, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 272269312, | |
| "byteOffset": 0 | |
| } | |
| ], | |
| "md5sum": "8eb6db1361ff93ffc8ffccccead35eb2" | |
| }, | |
| { | |
| "dataPath": "params_shard_1.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29826560, | |
| "records": [ | |
| { | |
| "name": "model.layers.0.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 1792 | |
| }, | |
| { | |
| "name": "model.layers.0.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8718080 | |
| }, | |
| { | |
| "name": "model.layers.0.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26152448 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26154752 | |
| }, | |
| { | |
| "name": "model.layers.0.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28219136 | |
| }, | |
| { | |
| "name": "model.layers.1.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29824768 | |
| } | |
| ], | |
| "md5sum": "6fe85c8fe13fe24ebd9edda71a33d392" | |
| }, | |
| { | |
| "dataPath": "params_shard_2.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.1.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.1.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.1.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.1.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.10.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "293231cff26aba3c77b107c0d27244dc" | |
| }, | |
| { | |
| "dataPath": "params_shard_3.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.10.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.10.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.10.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.10.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.11.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "85ea8209314eae6bd034c22b22cb5c5a" | |
| }, | |
| { | |
| "dataPath": "params_shard_4.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.11.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.11.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.11.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.11.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.12.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "a3961548ecfae7cced29bb94343a0726" | |
| }, | |
| { | |
| "dataPath": "params_shard_5.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.12.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.12.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.12.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.12.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.13.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "d6ff6a9b80001cc776e96fd3f6eaa0dd" | |
| }, | |
| { | |
| "dataPath": "params_shard_6.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.13.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.13.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.13.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.13.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.14.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "d10bb94ac2e98b9a1a8b3a9c4e7d87e0" | |
| }, | |
| { | |
| "dataPath": "params_shard_7.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.14.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.14.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.14.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.14.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.15.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "5fa5ef47f8b7c8e8e7bfd5b4e9ec743b" | |
| }, | |
| { | |
| "dataPath": "params_shard_8.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.15.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.15.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.15.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.15.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.16.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "55a545138af882a1c39218b2e8e11424" | |
| }, | |
| { | |
| "dataPath": "params_shard_9.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.16.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.16.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.16.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.16.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.17.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "7a5c3aa7d1c96a66cab677ae8fdeaaa3" | |
| }, | |
| { | |
| "dataPath": "params_shard_10.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.17.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.17.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.17.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.17.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.18.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "ff52265f4f00acfaae86600f79470e8a" | |
| }, | |
| { | |
| "dataPath": "params_shard_11.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.18.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.18.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.18.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.18.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.19.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "4e4a2b90ca189e6cc74fcb71b4c15793" | |
| }, | |
| { | |
| "dataPath": "params_shard_12.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.19.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.19.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.19.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.19.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.2.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "085f2b5d8d9716bc7a8f4419fc43d620" | |
| }, | |
| { | |
| "dataPath": "params_shard_13.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.2.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.2.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.2.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.2.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.20.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "705a2a5afb9a64737625de6e16951dcf" | |
| }, | |
| { | |
| "dataPath": "params_shard_14.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.20.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.20.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.20.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.20.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.21.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "c69a828a3acd4d90084c3ab3e861bf55" | |
| }, | |
| { | |
| "dataPath": "params_shard_15.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.21.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.21.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.21.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.21.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.22.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "9b3ab4317c9f88779f466f909fa3eefb" | |
| }, | |
| { | |
| "dataPath": "params_shard_16.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.22.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.22.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.22.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.22.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.23.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "f52e5ddce00b63da6223448922e40616" | |
| }, | |
| { | |
| "dataPath": "params_shard_17.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.23.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.23.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.23.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.23.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.3.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "34b6b8eba3eaac8f34c6a63e75224775" | |
| }, | |
| { | |
| "dataPath": "params_shard_18.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.3.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.3.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.3.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.3.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.4.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "4fa2f0ddbc4cdc9e4057341bb1f0099a" | |
| }, | |
| { | |
| "dataPath": "params_shard_19.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.4.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.4.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.4.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.4.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.5.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "fc7ec420c94e1f151049bc0ecc6e84e5" | |
| }, | |
| { | |
| "dataPath": "params_shard_20.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.5.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.5.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.5.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.5.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.6.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "c64f73311f88839d2411cd49e7690397" | |
| }, | |
| { | |
| "dataPath": "params_shard_21.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.6.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.6.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.6.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.6.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.7.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "bea37be5e40c86caa12ec12c58212660" | |
| }, | |
| { | |
| "dataPath": "params_shard_22.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.7.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.7.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.7.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.7.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.8.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "e7e7572b1cca278c2d1cd20ec1fa4f8e" | |
| }, | |
| { | |
| "dataPath": "params_shard_23.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.8.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.8.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.8.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.8.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.layers.9.input_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "4f3a57ae3ffb4a4cfee9c71d8b26bbc4" | |
| }, | |
| { | |
| "dataPath": "params_shard_24.bin", | |
| "format": "raw-shard", | |
| "nbytes": 29824768, | |
| "records": [ | |
| { | |
| "name": "model.layers.9.mlp.down_proj.weight", | |
| "shape": [ | |
| 896, | |
| 4864 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 8716288, | |
| "byteOffset": 0 | |
| }, | |
| { | |
| "name": "model.layers.9.mlp.gate_up_proj.weight", | |
| "shape": [ | |
| 9728, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 17432576, | |
| "byteOffset": 8716288 | |
| }, | |
| { | |
| "name": "model.layers.9.post_attention_layernorm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 26148864 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.bias", | |
| "shape": [ | |
| 1152 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2304, | |
| "byteOffset": 26150656 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.c_attn.weight", | |
| "shape": [ | |
| 1152, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 2064384, | |
| "byteOffset": 26152960 | |
| }, | |
| { | |
| "name": "model.layers.9.self_attn.o_proj.weight", | |
| "shape": [ | |
| 896, | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1605632, | |
| "byteOffset": 28217344 | |
| }, | |
| { | |
| "name": "model.norm.weight", | |
| "shape": [ | |
| 896 | |
| ], | |
| "dtype": "float16", | |
| "format": "f32-to-bf16", | |
| "nbytes": 1792, | |
| "byteOffset": 29822976 | |
| } | |
| ], | |
| "md5sum": "fbbdb3eaf48f6b7f28d1964554ded082" | |
| } | |
| ] | |
| } |