Upload GptOssForCausalLM

README.md

@@ -1,6 +1,8 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- trl
+- sft
 ---
 
 # Model Card for Model ID

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "GptOssForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "eos_token_id": 200002,
+  "experts_per_token": 4,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2880,
+  "initial_context_length": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 2880,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 131072,
+  "model_type": "gpt_oss",
+  "num_attention_heads": 64,
+  "num_experts_per_tok": 4,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "num_local_experts": 32,
+  "output_router_logits": false,
+  "pad_token_id": 199999,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "beta_fast": 32.0,
+    "beta_slow": 1.0,
+    "factor": 32.0,
+    "original_max_position_embeddings": 4096,
+    "rope_type": "yarn",
+    "truncate": false
+  },
+  "rope_theta": 150000,
+  "router_aux_loss_coef": 0.9,
+  "sliding_window": 128,
+  "swiglu_limit": 7.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
+  "use_cache": false,
+  "vocab_size": 201088
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c6e4921aa9cf5e88207fe26db8ec3ede29819c437a99ae2ebe6a22c4f0254e
+size 4504304664

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06142b31d80f754e9ad93d9b70b55ba1e9e53dca49169150eaf985024bdd26d0
+size 4939127656

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7ac27019ab2d8106bbc72d00d4b621be98e1d5263d0a4b27b63e30432ba4e9
+size 4939127656

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ace72c4425f3a2568ceafd3ec981a0ed6eb04e3da018851a3b5d2aa5a4c8997
+size 4939127680

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb3da72253fd9fccdd516109526650bb6a6a58a496933e2fda4cb80c101edad
+size 4939127704

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e0762aa1e1d8dc4f60343ef6921c2822460f3349a26c1b43a00fa553ea7095
+size 4939127704

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16f31dfed1caad33440b8e09f1c7f9dc9ed9b3a3b6f305b8f01519fdd17ba6e4
+size 4939127704

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f4e9ee7c2edd130cf2f771f085121fee3e3837dbab5a9715ecd71cbebc659f8
+size 4939127704

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9356faebad04af74fa7b5d7c71a65206fa4ffd8f48d65424651bc6a7aa81c0
+size 2751362856

model.safetensors.index.json

@@ -0,0 +1,419 @@
+{
+  "metadata": {
+    "total_parameters": 20914757184,
+    "total_size": 41829514368
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.router.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.router.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.sinks": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.down_proj": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.down_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.router.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.router.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.sinks": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.router.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.mlp.router.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.sinks": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.11.mlp.router.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.mlp.router.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.sinks": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.router.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.mlp.router.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.sinks": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.down_proj": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.down_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.router.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.mlp.router.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.sinks": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.14.mlp.router.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.mlp.router.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.sinks": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00005-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.router.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.mlp.router.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.sinks": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.down_proj": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.down_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.router.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.mlp.router.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.sinks": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.17.mlp.router.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.mlp.router.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.sinks": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00006-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.router.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.mlp.router.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.sinks": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.down_proj": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.down_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.router.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.mlp.router.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.sinks": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.2.mlp.router.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.router.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.sinks": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.20.mlp.router.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.mlp.router.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.sinks": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00007-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.router.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.mlp.router.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.sinks": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.down_proj": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.down_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.router.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.mlp.router.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.sinks": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.down_proj": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.down_proj_bias": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00009-of-00009.safetensors",
+    "model.layers.23.mlp.router.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.mlp.router.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.sinks": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00008-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.router.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.mlp.router.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.sinks": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.down_proj": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.down_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.router.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.mlp.router.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.sinks": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.5.mlp.router.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.router.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.sinks": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00002-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.router.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.mlp.router.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.sinks": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.down_proj": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.down_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.router.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.mlp.router.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.sinks": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.8.mlp.router.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.mlp.router.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.sinks": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00003-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.down_proj": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.down_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.router.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.mlp.router.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.sinks": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00004-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.safetensors"
+  }
+}