初始化项目，由ModelHub XC社区提供模型

Model: TinyPixel/lima-test
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.33.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.0.dev0"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b155f0ae6879873f439637807de8d9a95517178f4dedd27f818e214d00b57d
+size 981485368

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ee2437ccd19a92a123d2cdb67987319fd7478001f5b1d56e2b4b95c92066a2
+size 966838864

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fb91796ceba5000225592aaed078c1655f3e80c34267509efcdfedadca6bc35
+size 966822256

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406c2dfc80da80ded8e8d4da13ab73e93e09306d3af18d065393c387a1799582
+size 989907416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745caccda5465b17893c5d16934da2b4028686e7b8798b877926cd19c7485541
+size 943753712

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bffd811c2e7af975ba1df4835bfe6f346eb86a3973d2d232faac53d1e898c814
+size 989890824

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303b97079a11725622c3ef7b4da3378e348bcb0119fa7447e9e19457fef26960
+size 966838888

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29244590985f84c9b18e9d39cbb85100f8fab17ef751d583aae2a531835fe730
+size 966822272

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba10bf2d8280994eb2586ae646cc0598d77cafff2908ff158994c3fe2452cbe8
+size 989907440

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d6cc2ac2cd06997ea0abba08adac89ae28de0cfb21a2515172e0571ded78535
+size 943753720

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb33856ea988388fb8164561c6245cc40a7aa94997e46779f88697936e640910
+size 989890824

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b07c30468c3d4b033c7c5209e245f1754350f7a06e1d1b9bb9d56e92dd4892df
+size 966838888

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0127a167581a3254f08079fe32ef14fab86d30278e6a9b19eb123910d1a95ff6
+size 966822272

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c936870380598bf54f56e9d941f403222d609e922e1e1526991b8ed3140c35b
+size 847292072

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+    "metadata": {
+        "total_size": 13476831232
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00014-of-00014.safetensors",
+        "model.embed_tokens.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.input_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.mlp.up_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00014.safetensors",
+        "model.layers.10.input_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.10.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.10.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.11.input_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.11.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.11.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.12.input_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.12.mlp.down_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.12.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00014.safetensors",
+        "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.13.input_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.13.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.13.mlp.up_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00014.safetensors",
+        "model.layers.14.input_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.14.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.14.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.15.input_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.15.mlp.down_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.15.mlp.up_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00014.safetensors",
+        "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.16.input_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.16.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.16.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00014.safetensors",
+        "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.17.mlp.down_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.17.mlp.up_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00014.safetensors",
+        "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.18.input_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.18.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.18.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00014.safetensors",
+        "model.layers.19.input_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.19.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.19.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.20.input_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00009-of-00014.safetensors",
+        "model.layers.20.self_attn.k_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.20.self_attn.o_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.20.self_attn.q_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.20.self_attn.v_proj.weight": "model-00009-of-00014.safetensors",
+        "model.layers.21.input_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00014.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.23.input_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.23.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.23.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00014.safetensors",
+        "model.layers.24.input_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.24.mlp.down_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.24.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.24.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.24.post_attention_layernorm.weight": "model-00011-of-00014.safetensors",
+        "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.24.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.24.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.25.input_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.25.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.25.mlp.gate_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.25.mlp.up_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.25.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.25.self_attn.o_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.25.self_attn.q_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00014.safetensors",
+        "model.layers.26.input_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.26.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.26.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.26.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.26.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.26.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.26.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.26.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.27.input_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.27.mlp.down_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.27.mlp.gate_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.27.mlp.up_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.27.post_attention_layernorm.weight": "model-00012-of-00014.safetensors",
+        "model.layers.27.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.27.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.27.self_attn.v_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.28.input_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.28.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.28.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.28.self_attn.k_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.28.self_attn.q_proj.weight": "model-00012-of-00014.safetensors",
+        "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.29.input_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.29.mlp.down_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.29.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.29.mlp.up_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.29.post_attention_layernorm.weight": "model-00013-of-00014.safetensors",
+        "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors",
+        "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.30.input_layernorm.weight": "model-00014-of-00014.safetensors",
+        "model.layers.30.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+        "model.layers.30.mlp.gate_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.30.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+        "model.layers.30.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+        "model.layers.30.self_attn.k_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.30.self_attn.o_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.30.self_attn.q_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.30.self_attn.v_proj.weight": "model-00013-of-00014.safetensors",
+        "model.layers.31.input_layernorm.weight": "model-00014-of-00014.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00014-of-00014.safetensors",
+        "model.layers.31.mlp.gate_proj.weight": "model-00014-of-00014.safetensors",
+        "model.layers.31.mlp.up_proj.weight": "model-00014-of-00014.safetensors",
+        "model.layers.31.post_attention_layernorm.weight": "model-00014-of-00014.safetensors",
+        "model.layers.31.self_attn.k_proj.weight": "model-00014-of-00014.safetensors",
+        "model.layers.31.self_attn.o_proj.weight": "model-00014-of-00014.safetensors",
+        "model.layers.31.self_attn.q_proj.weight": "model-00014-of-00014.safetensors",
+        "model.layers.31.self_attn.v_proj.weight": "model-00014-of-00014.safetensors",
+        "model.layers.4.input_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.4.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.4.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00014.safetensors",
+        "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.5.input_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.5.mlp.down_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.5.mlp.up_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00014.safetensors",
+        "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.6.input_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.6.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.6.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00014.safetensors",
+        "model.layers.7.input_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.7.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.7.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.8.input_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.8.mlp.down_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.8.mlp.up_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00014.safetensors",
+        "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00014.safetensors",
+        "model.layers.9.input_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00014.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00014.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00005-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 sha256:2100d6665c31978c8d16a890ffdaf4aafe16bfab33a59cc571f1c19bcae3e54a
+size 981489327

pytorch_model-00002-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03f8fac29c831a40acbfcf59804450334aa87f2d0bbd8d6cfa16f88551c3dfa
+size 966844269

pytorch_model-00003-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010aad66bc06c44d4d133e6ae0d3817be734c38e497ecce259c0bb8225cc0a78
+size 966827273

pytorch_model-00004-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af564be95b58c6029c6b32e886bd54d7a26c32b87640ce21664bafbc11679625
+size 989912603

pytorch_model-00005-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc7ead743de32fb1c5ffae5208217492f0d5868f69e5dd0b5aaaf99e1d8a496
+size 943758939

pytorch_model-00006-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a1d314defa9c4d16ea0dd3b0db2e4645736d3ea50f94ce0849aa0b4e007ac77
+size 989895607

pytorch_model-00007-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b2c0668b3d9d8ad72ace5e999086c57c92208f49d4bde1658af0ecf8b617f1a
+size 966844269

pytorch_model-00008-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4375c027c3b46ce78b49583e0a83c864f2ed5a17a9e07912c743d03736c63c
+size 966827273

pytorch_model-00009-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f220b204b4cd5b6eb1c44a3e5306ac77fee0b67b69374b1ef881ea4d152437f
+size 989912667

pytorch_model-00010-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9aa67b26c7607344e10e31129eda9813fd8622bdf53ca03c4343f090149c12d
+size 943758939

pytorch_model-00011-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b3ce9b6c73382b71adb912b681871e72073116b7e3a7f8a79fe90c3c028b7b
+size 989895607

pytorch_model-00012-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cad9a8f57295158201737a5c7716d412ba40c5fdd191f8001225cebcfb7a16a6
+size 966844269

pytorch_model-00013-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20e891db57d51bad174de2cc726c604f6e3b3d0811f299948a9d1ffd2951a111
+size 966827273

pytorch_model-00014-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59cd47205d1779f60d0bb1838f4d33d70c18963abdcbc6dc14e8d02075621d62
+size 847295773

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 13476831232
+  },
+  "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-00002-of-00014.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-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-00002-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-00005-of-00014.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-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-00002-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-00002-of-00014.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00013-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-00014-of-00014.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-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-00003-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-00003-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-00003-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-00003-of-00014.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-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-00004-of-00014.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-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-00004-of-00014.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-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-00004-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-00004-of-00014.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.norm.weight": "pytorch_model-00014-of-00014.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}