Upload folder using huggingface_hub

config.json

@@ -47,15 +47,6 @@
   "num_local_experts": 32,
   "output_router_logits": false,
   "pad_token_id": 200017,
-  "quantization_config": {
-    "modules_to_not_convert": [
-      "model.layers.*.self_attn",
-      "model.layers.*.mlp.router",
-      "model.embed_tokens",
-      "lm_head"
-    ],
-    "quant_method": "mxfp4"
-  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "beta_fast": 32.0,
@@ -70,7 +61,8 @@
   "sliding_window": 128,
   "swiglu_limit": 7.0,
   "tie_word_embeddings": false,
-  "transformers_version": "4.56.0.dev0",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.55.0",
   "unsloth_fixed": true,
   "use_cache": true,
   "vocab_size": 201088

generation_config.json

@@ -6,5 +6,5 @@
     199999
   ],
   "pad_token_id": 199999,
-  "transformers_version": "4.55.0.dev0"
+  "transformers_version": "4.56.0.dev0"
 }

model-00000-of-00002.safetensors → model-00001-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d0f997dcfc4462089d536bffe51b4bcea2f872f5c430be09ef8ed392312427
-size 4792272488
+oid sha256:dc729189133161b61e287dd7bdec06afc2b7f77ed1820ca53eda0553fa742230
+size 4504304664

model-00001-of-00002.safetensors → model-00002-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fbe328ab445455d6f58dc73852b85873bd626986310abd91cd4d2ce3245eaea
-size 4798702184
+oid sha256:a4708b3da84cd7d559f5cd2eb9d0d13466ae1ccd90fdee8295d9ec3d8748582c
+size 4939127656

model-00002-of-00002.safetensors → model-00003-of-00009.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a18106b209e9ab35c3406db4f6f12a927364a058b21e9d1373d682e20674b303
-size 4170342232
+oid sha256:96031fa4efe1e880b2f17ac4352c3a2d251129d8140d122b9e8649a2d45c51d2
+size 4939127656

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e221c089ddcbacd6f4495a2dfccea2206cb8b21795ea868415125e9fb8139e
+size 4939127680

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f223ae981c1c8f4925334b8e0954ce78a613b0602d3eba28ea73f0146c9d73f3
+size 4939127704

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf0e3a0ccf931369e3ebe77f1f6d0a1781d739d6cb1dfed7c54fedda3f94fe18
+size 4939127704

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a3ad356e1a0d63de63f78975caf1a129d7d29bc00a7614de652aff7a4c57b0
+size 4939127704

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07a2d79388f1f6f1bebac3d03216b6ac47c2bf498640ab54ac8c15beb629847f
+size 4939127704

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1951ff65d233bcb7f50485d294cced6497b8e0d9707f57087912fc2352492e
+size 2751362856

model.safetensors.index.json

@@ -1 +1,419 @@
-{"metadata": {"total_size": 13761264768}, "weight_map": {"model.layers.0.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.0.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.0.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.0.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.0.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.1.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.1.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.1.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.1.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.1.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.10.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.10.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.10.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.10.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.10.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.11.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.11.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.11.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.11.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.11.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.12.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.12.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.12.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.12.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.12.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.13.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.13.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.13.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.13.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.13.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.14.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.14.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.14.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.14.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.14.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.15.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.15.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.15.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.15.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.15.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.16.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.16.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.16.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.16.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.16.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.17.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00000-of-00002.safetensors", "model.layers.17.self_attn.sinks": "model-00000-of-00002.safetensors", "model.layers.17.mlp.router.bias": "model-00000-of-00002.safetensors", "model.layers.17.mlp.router.weight": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.gate_up_proj_bias": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.gate_up_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.gate_up_proj_scales": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.down_proj_bias": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.down_proj_blocks": "model-00000-of-00002.safetensors", "model.layers.17.mlp.experts.down_proj_scales": "model-00000-of-00002.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.18.input_layernorm.weight": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.o_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00000-of-00002.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.18.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.18.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.18.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.18.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.19.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.19.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.19.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.19.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.2.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.2.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.2.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.2.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.20.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.20.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.20.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.20.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.21.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.21.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.21.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.21.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.22.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.22.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.22.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.22.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.23.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.23.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.23.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.23.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.3.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.3.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.3.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.3.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.4.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.4.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.4.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.4.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.5.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.5.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.5.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.gate_up_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.gate_up_proj_scales": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.down_proj_bias": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.down_proj_blocks": "model-00001-of-00002.safetensors", "model.layers.5.mlp.experts.down_proj_scales": "model-00001-of-00002.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors", "model.layers.6.self_attn.sinks": "model-00001-of-00002.safetensors", "model.layers.6.mlp.router.bias": "model-00001-of-00002.safetensors", "model.layers.6.mlp.router.weight": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.gate_up_proj_bias": "model-00001-of-00002.safetensors", "model.layers.6.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.6.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.7.self_attn.sinks": "model-00002-of-00002.safetensors", "model.layers.7.mlp.router.bias": "model-00002-of-00002.safetensors", "model.layers.7.mlp.router.weight": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.gate_up_proj_bias": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.7.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.8.self_attn.sinks": "model-00002-of-00002.safetensors", "model.layers.8.mlp.router.bias": "model-00002-of-00002.safetensors", "model.layers.8.mlp.router.weight": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.gate_up_proj_bias": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.8.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00002.safetensors", "model.layers.9.self_attn.sinks": "model-00002-of-00002.safetensors", "model.layers.9.mlp.router.bias": "model-00002-of-00002.safetensors", "model.layers.9.mlp.router.weight": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.gate_up_proj_bias": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.gate_up_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.gate_up_proj_scales": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.down_proj_bias": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.down_proj_blocks": "model-00002-of-00002.safetensors", "model.layers.9.mlp.experts.down_proj_scales": "model-00002-of-00002.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors", "model.embed_tokens.weight": "model-00002-of-00002.safetensors", "model.norm.weight": "model-00002-of-00002.safetensors", "lm_head.weight": "model-00002-of-00002.safetensors"}}
+{
+  "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"
+  }
+}