HF 4.32

config.json

@@ -20,7 +20,7 @@
   "rope_scaling": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.32.0.dev0",
   "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -5,5 +5,5 @@
   "pad_token_id": 0,
   "temperature": 0.9,
   "top_p": 0.6,
-  "transformers_version": "4.31.0"
+  "transformers_version": "4.32.0.dev0"
 }

model-00001-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea9214a64cb4c5a64bfa7516ff67b36d338696e1e9ef0ca70eab14d10eeba488
-size 1947774712
+oid sha256:3d3eb91816affeb64fc1f1a4e01a86eaf6a9f1df84d1f99507dc82312f84304a
+size 1947773640

model-00002-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a64f902b1767bd1072da2490ab5b7fdc6206ffe18231b213da8a26b200991ec9
-size 1903231048
+oid sha256:5080365135be5097e54c945ba2d9989fad541127ac6d92c8d9cb60d67cca73ba
+size 1903229976

model-00003-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73cb95ad15f2ef70880760dcb74266f1bdd6366ae44705f5b5d7ab4484bbb3d8
-size 1903231048
+oid sha256:30218f9b6ab6af8fe6ba88378add37d45d5e282cfab17969e1bb8887648981a0
+size 1903229976

model-00004-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45723fab9476047c5db061bf9994e2363d275aadf45eb632057b72016eee10aa
-size 1903231064
+oid sha256:0f22c8a3f8b3dc8001182018f6b3087498e2e47bff8f9ecbfcba9a1cb717dc63
+size 1903229992

model-00005-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce33c50f2bf7e674b073ac7f98a7912d8ca2168791b3bd6eec2a602699952d85
-size 1903231080
+oid sha256:2392331eb3fc7212ec02734d819fbad568467ae7c21897edfb73c421928d4fc6
+size 1903230008

model-00006-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eadac2da7131a5b9d0cec9691f4814649625567c290cd8269330ff8537d77a34
-size 1903231080
+oid sha256:f4de532f58a6829499f8681e957cfdc45b59331a616f1cf07a73305a22b2b23a
+size 1903230008

model-00007-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa7d86953cbe4379836253959928c8d1afcf9544270c7159a15530259c8aede4
-size 1903231080
+oid sha256:c544675d8a94c1a685b0e717c2646134618e2249da93f529f246248110f5233a
+size 1903230008

model-00008-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122f3f8c621b3c9e6d4be557672a89bbbe5fb8a01679f54c54e498cf2495600b
-size 1903231080
+oid sha256:0116341747a3a1bde448abe4a533081775c11a842ca69a8fefa321af34d0b33a
+size 1903230008

model-00009-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83aea0a2c6153b464ac1c8d3b69714b5f8719f80d0b7b465d50a01bfda3206e
-size 1903231080
+oid sha256:f8c9948db79a0a729337922806b558647c94e94e9a3a03a69505562c428c6908
+size 1903230008

model-00010-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7835efe9433c57f4d8a3dddf70cef4776a62f705741c44db2b5579ccaf62856
-size 1903231080
+oid sha256:8915f00c9e86f552d5302469bc69b43568fae189efdc330d7f0f75f2692a1200
+size 1903230008

model-00011-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1340b7ea74c26f6d774b7151894c9c9b9b61bf74042b7b214959173d74c7708a
-size 1903231080
+oid sha256:b9a80aa4a01a58c3d95aba31f4c2927456bdedf5e0b3f501e154a438cd10ecac
+size 1903230008

model-00012-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0ee1b3e97bead2e85c13732274e85ce59bf5071f124c3b70b39d24c680e85e
-size 1903231080
+oid sha256:2465f4ddbc09c1a32c860ff9769e6aeee121497a85f72b63d42297047a91849c
+size 1903230008

model-00013-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f965cad34ddbff55cf912aafa5e647c9a1746504c81624b6585deef73e1d7ed
-size 1903231080
+oid sha256:1c7f46e8a89cf8432229e7838a8c15b706fb9f36620987d19380a42b5b7bce0b
+size 1903230008

model-00014-of-00014.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7e7e9841385b69903a6d7517bdbf0581d1f39664bd2e1baabd4a1392c613c12
-size 1245237264
+oid sha256:f5055f20b22d2b17f95dec4fa5d07f3be9648c0132a0575f0b0f7aa3338d11fd
+size 1245236904

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 26031738880
+    "total_size": 26031728640
   },
   "weight_map": {
     "lm_head.weight": "model-00014-of-00014.safetensors",
@@ -13,7 +13,6 @@
     "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",
@@ -23,7 +22,6 @@
     "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",
@@ -33,7 +31,6 @@
     "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",
@@ -43,7 +40,6 @@
     "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",
@@ -53,7 +49,6 @@
     "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",
@@ -63,7 +58,6 @@
     "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",
@@ -73,7 +67,6 @@
     "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",
@@ -83,7 +76,6 @@
     "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",
@@ -93,7 +85,6 @@
     "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",
@@ -103,7 +94,6 @@
     "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",
@@ -113,7 +103,6 @@
     "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",
@@ -123,7 +112,6 @@
     "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",
@@ -133,7 +121,6 @@
     "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",
@@ -143,7 +130,6 @@
     "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",
@@ -153,7 +139,6 @@
     "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",
@@ -163,7 +148,6 @@
     "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",
@@ -173,7 +157,6 @@
     "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",
@@ -183,7 +166,6 @@
     "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",
@@ -193,7 +175,6 @@
     "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",
@@ -203,7 +184,6 @@
     "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",
@@ -213,7 +193,6 @@
     "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",
@@ -223,7 +202,6 @@
     "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",
@@ -233,7 +211,6 @@
     "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",
@@ -243,7 +220,6 @@
     "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",
@@ -253,7 +229,6 @@
     "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",
@@ -263,7 +238,6 @@
     "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",
@@ -273,7 +247,6 @@
     "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",
@@ -283,7 +256,6 @@
     "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",
@@ -293,7 +265,6 @@
     "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",
@@ -303,7 +274,6 @@
     "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",
@@ -313,7 +283,6 @@
     "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",
@@ -323,7 +292,6 @@
     "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",
@@ -333,7 +301,6 @@
     "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",
@@ -343,7 +310,6 @@
     "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",
@@ -353,7 +319,6 @@
     "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",
@@ -363,7 +328,6 @@
     "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",
@@ -373,7 +337,6 @@
     "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",
@@ -383,7 +346,6 @@
     "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",
@@ -393,7 +355,6 @@
     "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",
@@ -403,7 +364,6 @@
     "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-00001-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bde146f45c778df6532713881cd9bbf5b76ede26b17eaba948cc8bfcb1f20a91
+size 1947779007

pytorch_model-00002-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f038273e8c54913e92a7d8d0c4a8e976ea30c422eb1a442bf65aa4185949a16f
+size 1903235957

pytorch_model-00003-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edbb93511d0b62bc14bc984462d50dcf267659adcb567c0a9a71320e09f3de36
+size 1903235957

pytorch_model-00004-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df35468a0f604a84a3ea16e0422d01345cd2845e9b7e38d59eab607a61ba0af
+size 1903235957

pytorch_model-00005-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bee1cbf712311b5ee758644b683c4188a7f36dcbdcca3242970b7e50096813
+size 1903235957

pytorch_model-00006-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ecde442b249ff36852709f95bd89814973cb677629a3e63331715c79812362
+size 1903235957

pytorch_model-00007-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86c544fa9ddc611c8eb8ba46bf9b5ca8d8bca051f52047fdacbb987988c16ab9
+size 1903235957

pytorch_model-00008-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c91a9016d0ebf239b12e0bd5c3eeaeec48ae08e825ea7b03e582db30351979
+size 1903235957

pytorch_model-00009-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75f1bb4728833877060d12e61971c04b1841b6693f19d66c5a69672a7d0fb20a
+size 1903235957

pytorch_model-00010-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3a3caf9553bbcabbf0044d0c857371bb840ba1622ff3c5f16feae5544174626
+size 1903235957

pytorch_model-00011-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd924169fd93b6a71033a8ed5dac38f409aeac954e90906001e4fed90615f84
+size 1903235957

pytorch_model-00012-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:185a51f31a5baff58a106da322b9299d27826790e2740ade35ee828a557fee65
+size 1903235957

pytorch_model-00013-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc016fc3dd5fc816c688c8924069b1c832d5c0e9a97e82ba5ffcbf8aa05d2f62
+size 1903235957

pytorch_model-00014-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a8779b8b848cd1296ad49f038e23c080f0401d33d23c3d53c7fef602a6c096
+size 1245240477

pytorch_model.bin.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 26031728640
+  },
+  "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-00014-of-00014.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00014-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-00014-of-00014.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00014-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-00014-of-00014.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00014-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-00014-of-00014.bin"
+  }
+}