初始化项目，由ModelHub XC社区提供模型

Model: TinyPixel/testmodel2
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": "4.33.2",
+  "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": "4.33.2"
+}

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f4bd81605f6ac30b81d6ae3e1cc87a8ab0d5cd75a6bbd29f0bd4d01a49289be
+size 981485368

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05f8f8f7c91bc54b7f016de19ac67d58336325c69c8dc488369ab2e5625492ed
+size 966838864

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859574c1d74e7bbe8f04b30e658099060418cab264a0971fe16b9e73aac58d44
+size 966822256

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f347fb2d583e132524ae25108f691191983a95765b8b144353dbc6464b9ae43a
+size 989907416

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae58aa68cf602349d7d557163f9765a444c4f6a331e260f7855c93593b9f7fbc
+size 943753712

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8765ce0c8daf69bc7be34d391502a2ad850e9fb4cbd2c5634da005ba95d77421
+size 989890824

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:827064f16341b9022fa46379c0199d84ae26538e8b9bb940133b81b25b94aff5
+size 966838888

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7003755fe6186f0585ffd908065155a1b3c87ded31d91d2512108f39be321c8a
+size 966822272

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1c9583625ebe837be7e20eafc75ad75729139960e692bf2762ccf3895a6060
+size 989907440

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e510dcb6de1b2bae842bebd0e4e8e20b5dbf9a090385c9ede48919184b8e405c
+size 943753720

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99e89dd1e2ada2ee2a93d760f833d4b7d44b9feb2ea39dad57eba3793dabaa30
+size 989890824

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcdb830e91ce5a84fb0e047b85f3624daa6b68bb4f6ebb35238b92fc08a60634
+size 966838888

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696741a10a743963e0d9a4d5f9db306cf04b40af5b32d2bcb576bd3cafc1d392
+size 966822272

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9432f0cc1b4d4b6e042d5b257af516174f78ee11c4f004f9cfa35950f04cd93
+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 sha256:4093c2cee185cda3ea87720f716c5ebdb413aee08fd97d1d173a1e6e214743bc
+size 981489327

pytorch_model-00002-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ee8804dbcc3d5b5b1b6e1c7fe28e6b0ad3b9e89f43b17175885d6588dda5c0
+size 966844269

pytorch_model-00003-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1f82ddc3e66cfe6d6d3d8fe9198b2810e26c9513b29486c779f992f5cfef4b2
+size 966827273

pytorch_model-00004-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a695ec5ecb22acb024897cab6c6b59f917eaf20d1ccedaed2b600c24365e3b5a
+size 989912603

pytorch_model-00005-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52f93ecd30e8a28f86307e81238931abda5e11472104f6041512fe43db7a194a
+size 943758939

pytorch_model-00006-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2d5df99ebd17bb3b14d157f116670d53b0995bc130eef84a4a9c31e75e02d8
+size 989895607

pytorch_model-00007-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79228fb1138cf98f8e2b5826c1d3b19319d4c9c42d9b3218d7d90d096b49b706
+size 966844269

pytorch_model-00008-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a951737a87da7af4d0ced6aa9bd83e9df7284d961b2bd15c8d9582de0d216d
+size 966827273

pytorch_model-00009-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75beca737b83f208b5ce0ff83ac2519efae738e0e0fa38883aa0144c9f45503c
+size 989912667

pytorch_model-00010-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319e8343c754520fdd7403a74c3a6d99ee5623c4c51717fb7b1b469e69872f6e
+size 943758939

pytorch_model-00011-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b4d79f9e593245c7b50ebcb11e17a54e1d5cb1c55a37edff0785f394064b1a
+size 989895607

pytorch_model-00012-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bcbd041e057d93861b380f5660f4285354c929630f096a631ea266cf80b7acc
+size 966844269

pytorch_model-00013-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a4d0bc49e3a04b15c1114acb29ad09e93912c768a6e981c0f6a050c8b14fc92
+size 966827273

pytorch_model-00014-of-00014.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ffb5923521c250d58a63c965158c15224c663d9fe31b66fa7cb50127aba911b
+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_config.json

@@ -0,0 +1,36 @@
+{
+  "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
+  },
+  "max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true
+}