Fixed version

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-13b-hf",
+  "_name_or_path": "mrseeker/llama2-13b-pike-v2-2",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -20,7 +20,7 @@
   "rope_scaling": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.32.0.dev0",
+  "transformers_version": "4.31.0",
   "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -1,8 +1,9 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "max_length": 4096,
   "pad_token_id": 0,
-  "transformers_version": "4.32.0.dev0",
-  "use_cache": false
+  "temperature": 0.9,
+  "top_p": 0.6,
+  "transformers_version": "4.31.0"
 }

pytorch_model-00001-of-00014.bin → model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc50eb0bbd2a12249a6166b5770ea063a37745973cc2f8e35ff18ebc5fc281c
-size 1947779263
+oid sha256:ea9214a64cb4c5a64bfa7516ff67b36d338696e1e9ef0ca70eab14d10eeba488
+size 1947774712

pytorch_model-00002-of-00014.bin → model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:314f3f58d5f02d5420d4377c1ca504c7463c07fef48140db940a34267606c4ef
-size 1903236213
+oid sha256:a64f902b1767bd1072da2490ab5b7fdc6206ffe18231b213da8a26b200991ec9
+size 1903231048

pytorch_model-00003-of-00014.bin → model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f5baa5f4ba5798e0528b2bcb086dacf7dd8664c7e129906a899b01a3243ca50
-size 1903236213
+oid sha256:73cb95ad15f2ef70880760dcb74266f1bdd6366ae44705f5b5d7ab4484bbb3d8
+size 1903231048

pytorch_model-00004-of-00014.bin → model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82bebb94aa47014d5bd9917766e3a17ee032a03115da9f6ac2f6b2e29e09c362
-size 1903236213
+oid sha256:45723fab9476047c5db061bf9994e2363d275aadf45eb632057b72016eee10aa
+size 1903231064

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce33c50f2bf7e674b073ac7f98a7912d8ca2168791b3bd6eec2a602699952d85
+size 1903231080

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eadac2da7131a5b9d0cec9691f4814649625567c290cd8269330ff8537d77a34
+size 1903231080

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa7d86953cbe4379836253959928c8d1afcf9544270c7159a15530259c8aede4
+size 1903231080

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:122f3f8c621b3c9e6d4be557672a89bbbe5fb8a01679f54c54e498cf2495600b
+size 1903231080

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b83aea0a2c6153b464ac1c8d3b69714b5f8719f80d0b7b465d50a01bfda3206e
+size 1903231080

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7835efe9433c57f4d8a3dddf70cef4776a62f705741c44db2b5579ccaf62856
+size 1903231080

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1340b7ea74c26f6d774b7151894c9c9b9b61bf74042b7b214959173d74c7708a
+size 1903231080

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f0ee1b3e97bead2e85c13732274e85ce59bf5071f124c3b70b39d24c680e85e
+size 1903231080

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f965cad34ddbff55cf912aafa5e647c9a1746504c81624b6585deef73e1d7ed
+size 1903231080

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7e7e9841385b69903a6d7517bdbf0581d1f39664bd2e1baabd4a1392c613c12
+size 1245237264

model.safetensors.index.json

@@ -0,0 +1,410 @@
+{
+  "metadata": {
+    "total_size": 26031738880
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00014-of-00014.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00014.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00014.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00004-of-00014.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00004-of-00014.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00005-of-00014.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00006-of-00014.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00006-of-00014.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00006-of-00014.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00007-of-00014.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00007-of-00014.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00014.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00007-of-00014.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00008-of-00014.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00009-of-00014.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00009-of-00014.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00009-of-00014.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00010-of-00014.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00002-of-00014.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00011-of-00014.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00011-of-00014.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.rotary_emb.inv_freq": "model-00011-of-00014.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.rotary_emb.inv_freq": "model-00012-of-00014.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.rotary_emb.inv_freq": "model-00012-of-00014.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.rotary_emb.inv_freq": "model-00012-of-00014.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.rotary_emb.inv_freq": "model-00013-of-00014.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.rotary_emb.inv_freq": "model-00014-of-00014.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00002-of-00014.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00002-of-00014.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00003-of-00014.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00004-of-00014.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+    "model.norm.weight": "model-00014-of-00014.safetensors"
+  }
+}

pytorch_model-00005-of-00014.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2bce1b93999bd2fd3c498fdf4c8a2f6d204e726a09ef0226069d68819ffa5fc1
-size 1903236277

pytorch_model-00006-of-00014.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6e49612fd7f2779e1cb183f2ac44dccc98ff4ec93fcbd632713f130ad6feaf5d
-size 1903236277

pytorch_model-00007-of-00014.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:82a8a2cc7772932142b0098110bf19caa464e3f90c7786249e78117209098f28
-size 1903236277

pytorch_model-00008-of-00014.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a7c46c614d691923b77b6566c9be5c3a7aabf71629f8f50d50a27e791a03a228
-size 1903236277

pytorch_model-00009-of-00014.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9d1870603c36116b3f67d40b28d32031958deb7e704be6311b8ff85be40a8703
-size 1903236277

pytorch_model-00010-of-00014.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a959d5aff13b34c5a2fe43851275fc4a9b96b56fd2d9688f0c0081d6c02cec8a
-size 1903236277

pytorch_model-00011-of-00014.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3d400072947a4eb54fc1a7ba4ecbc97acb0f2eb24249947a6cff71e8260962b4
-size 1903236277

pytorch_model-00012-of-00014.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:755cc10b2b850fedaf8ea495911d46922858af5996f726e38e1117242146d1d3
-size 1903236277

pytorch_model-00013-of-00014.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2929fc661b4f3ffe7e8958f529595ec791fdd09e4f77030ccffa3593b6616970
-size 1551963227

pytorch_model-00014-of-00014.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4cd2fb58c9e65210d53d13cd7342c14f2757509fee101e7cebfd58c508110986
-size 665

pytorch_model.bin.index.json

@@ -1,370 +0,0 @@
-{
-  "metadata": {
-    "total_size": 24956897280
-  },
-  "weight_map": {
-    "lm_head.weight": "pytorch_model-00014-of-00014.bin",
-    "model.embed_tokens.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.11.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.14.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
-    "model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.17.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
-    "model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
-    "model.layers.20.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
-    "model.layers.21.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.22.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.23.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
-    "model.layers.24.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.25.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.26.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
-    "model.layers.27.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.28.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.29.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
-    "model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.30.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.31.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.32.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
-    "model.layers.33.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.34.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.35.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
-    "model.layers.36.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.37.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.38.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.39.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
-    "model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
-    "model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.8.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
-    "model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
-    "model.norm.weight": "pytorch_model-00013-of-00014.bin"
-  }
-}