Add 5B korean trained model, test version.

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "meta-llama/Llama-2-7b-hf",
   "architectures": [
     "LlamaForCausalLM"
   ],
@@ -21,7 +20,7 @@
   "rope_scaling": null,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.31.0",
+  "transformers_version": "4.28.0.dev0",
   "use_cache": true,
   "vocab_size": 46336
 }

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.0.dev0"
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5192269ecced5ec360840cac19cb3d289e9ec678aa2138c6ef3eef4dbda10a8c
+size 918571280

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28fc0d376bb0ac17b494788b9a43d1a7e9c55382dc278b665705d3eacca6e925
+size 989891504

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63fede094ee1f645683a2ebf27e1b29c50dac992f51e657e268c438485c92e6c
+size 966839552

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81eebf38c5be5519aa32ff9fbf91d15f448143589f3d60adb4f08a091b8dd7b9
+size 966823304

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba82c3b277495d75496a4f4f783123062e30c28b16f1f0a0a6228cdcf4e3265e
+size 989908120

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5262174667db05e5fd35f5738948365916bf609789f50837433fabbb68a1386
+size 943754776

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b35abaed574d309d505b06f11b4c461f184a3fc7453e787e66163f6637574af7
+size 989891528

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d92a45e1710a2af9d256e8986624a705e39f906ea1ef2f1da67a7417484f1e
+size 966839576

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d853a4b19abe3140e9fb7447082c7f18302b51c5c774896c4c5476e182fc95e5
+size 966823328

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ea0608d3679ebb83d56cba2a8c7e998970eed314f7e043f5e7da32a7d390d5
+size 989908136

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bf99ebb30fab37b532df752d544d2f61ebb038f3ea005c9977034c96ebce669
+size 943754776

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece0e522c8a97ce497a8a45a52fe034fd25a8a63ee76adf0afdce44e398a0fdf
+size 989891528

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a2eac299765bbe4427e865b2a7946d285b19446e58263d039264ddade17d061
+size 966839576

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd49b00dc2666ebad796dab7411a9302c76bb1436b701e11bbe7beae0d8c709
+size 742435416

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b19e7afbde07dd5f11c93b2686f7b2425e63d4ef1d052ee3721edd47e991a51e
+size 379584640

model.safetensors.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 13711720448
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00015-of-00015.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00015.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00006-of-00015.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00007-of-00015.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00008-of-00015.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00009-of-00015.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00010-of-00015.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00011-of-00015.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00012-of-00015.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00013-of-00015.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00002-of-00015.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00014-of-00015.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00003-of-00015.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00004-of-00015.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00005-of-00015.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
+    "model.norm.weight": "model-00014-of-00015.safetensors"
+  }
+}

pytorch_model-00001-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ffc57a6c862b8192e2e5ccd823b2e0e25dcd8ba0941e4a9a466427033c5cdff
+size 918575087

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bef44e5f2194f7992ec671e618856c96960cfe955e8fc172925f99e9066341aa
+size 989896539

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a878d4a7cfe2fb6066f9e8d6792f9724b5b5170f488bfdfcee7b08c2d226cde9
+size 966845201

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c3fdab7cca65167c09f368b2235c76a5c3052f34b1e4e4a5b6e20ca044d4ce
+size 966828735

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2332e386eb91f9c8b681617a6d4f5a75470a88b1658a3438990b002049ecca24
+size 989913535

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f481fea4ebbceab66af4a6eaa313c428da6e309d47b465fd0ed3b206f29fd62
+size 943760401

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41fc4498a3d885be38e105062d73ad9115132f3c301980e85a1540624668937a
+size 989896539

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79cc5f22424065c8cd3f26463275493c143af3f0aa633923dfd7c5bd35c584c
+size 966845201

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86777950afd5baa937235ac2b9e63da6726af6ce189a1ed48947b7a9f9af3bb
+size 966828799

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4915966a10e705b89787ebc32944527d5ce0cd72b1ada1c6ebb750bb6eb89ed2
+size 989913535

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a3eadf55a0256c03e74214504aeda6847117e5f9b469594943ee5f2edb8ea36
+size 943760401

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:926900b36685d702f5954afcbada8f26c582319ae8d33be8255d7dc44cb5059f
+size 989896539

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b75a9936c3baa096cc28c7dd3aeee0ce9cd8a4ce62bbd376aaab9e8f5f36354f
+size 966845201

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c3527405df13b76a59fe831f9339bf628143dc1958a3f57582088c7cb4dc07
+size 742439845

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b4180f67def343ae9318471aa21d2af89c32f619761af73b3e812fe19060ce
+size 379585450

pytorch_model.bin.index.json

@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 13711720448
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00015-of-00015.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00015.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00015.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00015.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00009-of-00015.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00015.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00015.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00015.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00015.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00015.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00015.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00015.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00015.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00015.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.norm.weight": "pytorch_model-00014-of-00015.bin"
+  }
+}