Adding `safetensors` variant of this model (#2)

- Adding `safetensors` variant of this model (b0f5d429e9eeed628a68bccdbbf4d32cbee427d2)


Co-authored-by: Safetensors convertbot <[email protected]>

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f3780b8e185fb039bbb19be99f042bf3a01cfa4a9a782bae1bcae3d03271d9d
+size 2147483800

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d812efdea45f2cc58902496ecf92d941aca8f19803f092b5c7aa4eaa2fba992
+size 1879551864

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881da83f92924aefce8a38f3b81c038f5615edc0f93a1b59ecdb33ec1c077384
+size 1879560568

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fbe16a4cbaf9f1d9273df5acb4d2ee58d9c7adf800b094c3948531fc4b2d28a
+size 1980247488

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4586855855624d1f177ce8d3ddeb318af7db2d089d0b6bf43d965b1be739bdae
+size 1913123256

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7c8a36fbd851b98f1494598b59b6c47c62db952bb2b99656da2ed6edc526711
+size 1879551936

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09838f33ae418244848bea79c8edc14a2e988285f710e2c2b3bda51b8f0412a8
+size 1879560640

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5206b326750a0346ecbc1fc900af46b18ee65218909d60724378e1829a3bcaf
+size 1980247496

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e797f53c5197b27c5ab7bd3093496cebca53b0d496f5d8fba71b1f53a88e0988
+size 1107615264

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:503902f193085e270e65c2b516f8bd0e2ca58ca756c90deb710328e53cf0f880
+size 2147483792

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a53a4e777fb844845bc83383a949d57b0d9c0118c7a878cca1fc7e4d668738
+size 22126816

model.safetensors.index.json

@@ -0,0 +1,589 @@
+{
+    "metadata": {
+        "total_size": 18816477184
+    },
+    "weight_map": {
+        "language_model.lm_head.weight": "model-00010-of-00011.safetensors",
+        "language_model.model.embed_tokens.weight": "model-00001-of-00011.safetensors",
+        "language_model.model.final_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.final_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.0.input_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.dense.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.dense.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.k_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.k_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.q_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.q_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.query_key_value.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.0.self_attn.query_key_value.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.input_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.dense.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.dense.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.k_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.k_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.q_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.q_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.query_key_value.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.1.self_attn.query_key_value.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.10.input_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.dense.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.dense.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.k_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.k_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.q_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.q_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.query_key_value.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.10.self_attn.query_key_value.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.input_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.dense.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.dense.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.k_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.k_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.q_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.q_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.query_key_value.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.11.self_attn.query_key_value.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.input_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.dense.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.dense.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.k_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.k_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.q_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.q_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.query_key_value.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.12.self_attn.query_key_value.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.input_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.dense.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.dense.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.k_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.k_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.q_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.q_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.query_key_value.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.13.self_attn.query_key_value.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.14.input_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.dense.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.dense.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.k_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.k_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.q_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.q_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.query_key_value.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.14.self_attn.query_key_value.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.15.input_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.dense.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.dense.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.k_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.k_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.q_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.q_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.query_key_value.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.15.self_attn.query_key_value.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.input_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.dense.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.dense.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.k_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.k_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.q_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.q_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.query_key_value.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.16.self_attn.query_key_value.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.input_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.dense.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.dense.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.k_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.k_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.q_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.q_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.query_key_value.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.17.self_attn.query_key_value.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.input_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.dense_4h_to_h.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.dense_4h_to_h.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.dense_h_to_4h.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.mlp.dense_h_to_4h.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.dense.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.dense.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.k_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.k_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.q_layernorm.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.q_layernorm.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.query_key_value.bias": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.18.self_attn.query_key_value.weight": "model-00005-of-00011.safetensors",
+        "language_model.model.layers.19.input_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.dense.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.dense.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.k_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.k_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.q_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.q_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.query_key_value.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.19.self_attn.query_key_value.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.2.input_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.dense.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.dense.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.k_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.k_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.q_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.q_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.query_key_value.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.2.self_attn.query_key_value.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.20.input_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.dense.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.dense.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.k_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.k_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.q_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.q_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.query_key_value.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.20.self_attn.query_key_value.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.input_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.dense.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.dense.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.k_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.k_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.q_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.q_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.query_key_value.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.21.self_attn.query_key_value.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.input_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.dense_4h_to_h.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.dense_4h_to_h.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.dense.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.dense.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.k_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.k_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.q_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.q_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.query_key_value.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.22.self_attn.query_key_value.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.23.input_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.dense_h_to_4h.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.23.mlp.dense_h_to_4h.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.dense.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.dense.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.k_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.k_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.q_layernorm.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.q_layernorm.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.query_key_value.bias": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.23.self_attn.query_key_value.weight": "model-00006-of-00011.safetensors",
+        "language_model.model.layers.24.input_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.dense.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.dense.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.k_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.k_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.q_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.q_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.query_key_value.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.24.self_attn.query_key_value.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.input_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.dense.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.dense.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.k_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.k_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.q_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.q_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.query_key_value.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.25.self_attn.query_key_value.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.input_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.input_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.dense.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.dense.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.k_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.k_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.q_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.q_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.query_key_value.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.26.self_attn.query_key_value.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.input_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.dense_4h_to_h.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.dense_4h_to_h.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.dense_h_to_4h.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.mlp.dense_h_to_4h.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.dense.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.dense.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.k_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.k_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.q_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.q_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.query_key_value.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.27.self_attn.query_key_value.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.28.input_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.28.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.28.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.dense.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.dense.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.k_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.k_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.q_layernorm.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.q_layernorm.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.query_key_value.bias": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.28.self_attn.query_key_value.weight": "model-00007-of-00011.safetensors",
+        "language_model.model.layers.29.input_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.dense.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.dense.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.k_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.k_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.q_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.q_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.query_key_value.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.29.self_attn.query_key_value.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.3.input_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.dense_4h_to_h.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.dense.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.dense.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.k_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.k_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.q_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.q_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.query_key_value.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.3.self_attn.query_key_value.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.30.input_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.input_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.self_attn.dense.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.self_attn.dense.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.self_attn.k_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.self_attn.k_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.self_attn.q_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.self_attn.q_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.self_attn.query_key_value.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.30.self_attn.query_key_value.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.input_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.input_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.self_attn.dense.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.self_attn.dense.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.self_attn.k_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.self_attn.k_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.self_attn.q_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.self_attn.q_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.self_attn.query_key_value.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.31.self_attn.query_key_value.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.input_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.input_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.mlp.dense_4h_to_h.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.mlp.dense_4h_to_h.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.mlp.dense_h_to_4h.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.mlp.dense_h_to_4h.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.post_attention_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.self_attn.dense.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.self_attn.dense.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.self_attn.k_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.self_attn.k_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.self_attn.q_layernorm.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.self_attn.q_layernorm.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.self_attn.query_key_value.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.32.self_attn.query_key_value.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.33.input_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.self_attn.dense.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.self_attn.dense.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.self_attn.k_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.self_attn.k_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.self_attn.q_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.self_attn.q_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.33.self_attn.query_key_value.bias": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.33.self_attn.query_key_value.weight": "model-00008-of-00011.safetensors",
+        "language_model.model.layers.34.input_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.input_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.self_attn.dense.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.self_attn.dense.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.self_attn.k_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.self_attn.k_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.self_attn.q_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.self_attn.q_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.self_attn.query_key_value.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.34.self_attn.query_key_value.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.input_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.input_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.mlp.dense_4h_to_h.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.mlp.dense_4h_to_h.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.mlp.dense_h_to_4h.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.mlp.dense_h_to_4h.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.post_attention_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.self_attn.dense.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.self_attn.dense.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.self_attn.k_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.self_attn.k_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.self_attn.q_layernorm.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.self_attn.q_layernorm.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.self_attn.query_key_value.bias": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.35.self_attn.query_key_value.weight": "model-00009-of-00011.safetensors",
+        "language_model.model.layers.4.input_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.dense_h_to_4h.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.dense.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.dense.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.k_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.k_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.q_layernorm.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.q_layernorm.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.query_key_value.bias": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.4.self_attn.query_key_value.weight": "model-00002-of-00011.safetensors",
+        "language_model.model.layers.5.input_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.dense.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.dense.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.k_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.k_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.q_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.q_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.query_key_value.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.5.self_attn.query_key_value.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.input_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.dense.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.dense.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.k_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.k_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.q_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.q_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.query_key_value.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.6.self_attn.query_key_value.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.input_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.dense.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.dense.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.k_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.k_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.q_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.q_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.query_key_value.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.7.self_attn.query_key_value.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.input_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.dense_4h_to_h.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.dense_h_to_4h.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.dense.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.dense.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.k_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.k_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.q_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.q_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.query_key_value.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.8.self_attn.query_key_value.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.9.input_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.dense_4h_to_h.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.dense_4h_to_h.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.dense_h_to_4h.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.mlp.dense_h_to_4h.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.bias": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.dense.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.dense.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.k_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.k_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.q_layernorm.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.q_layernorm.weight": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.query_key_value.bias": "model-00003-of-00011.safetensors",
+        "language_model.model.layers.9.self_attn.query_key_value.weight": "model-00003-of-00011.safetensors",
+        "vision_embed_tokens.bias": "model-00011-of-00011.safetensors",
+        "vision_embed_tokens.weight": "model-00011-of-00011.safetensors"
+    }
+}