初始化项目，由ModelHub XC社区提供模型

Model: watcherShen/llama3-chinese-Instruct
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,51 @@
+---
+frameworks:
+- Pytorch
+license: Apache License 2.0
+tasks:
+- text-generation
+
+#model-type:
+##如 gpt、phi、llama、chatglm、baichuan 等
+#- gpt
+
+#domain:
+##如 nlp、cv、audio、multi-modal
+#- nlp
+
+#language:
+##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
+#- cn 
+
+#metrics:
+##如 CIDEr、Blue、ROUGE 等
+#- CIDEr
+
+#tags:
+##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
+#- pretrained
+
+#tools:
+##如 vllm、fastchat、llamacpp、AdaSeq 等
+#- vllm
+---
+### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
+#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
+
+SDK下载
+```bash
+#安装ModelScope
+pip install modelscope
+```
+```python
+#SDK模型下载
+from modelscope import snapshot_download
+model_dir = snapshot_download('watcherShen/llama3-chinese-Instruct')
+```
+Git下载
+```
+#Git模型下载
+git clone https://www.modelscope.cn/watcherShen/llama3-chinese-Instruct.git
+```
+
+<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/llm/data_hub/meta_llama3_instruct/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}

configuration.json

@@ -0,0 +1 @@
+{"framework":"Pytorch","task":"text-generation"}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "transformers_version": "4.40.1"
+}

model-00001-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1883860bc1015b63545497eb8f07fc78a12b49f4bc5e3028a5a86ba3feefa5d
+size 1050673296

model-00002-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39db0762c36af8a4e4a561c997c413cfbeb4dbde386e5309d7604ac00a5cb50c
+size 956336616

model-00003-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f03c624f1c263aa1d3eb97c1186cecd5fefb027eb881ffda6cc15c0317eae47
+size 989890696

model-00004-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0513c2008abff0363e9cb88ca770904e38d8e62ecb3140ae18a72470b6bf2909
+size 989890696

model-00005-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7110bed6fbb75a8e4fb1fa0a4939f400484ece6579aaa2e2a5aff0dfda2d5aba
+size 989907312

model-00006-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523635e71f4e4a44f04e677caeb4037f1d50b4278d39904a469ede178f86b81a
+size 956336624

model-00007-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab5822e5b429971438588e26d6662de6b3e9bfc2d797cb56230396b843c0366
+size 989890720

model-00008-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0cc82976441b15b747170f7aeacca24e90c1fbd98ade95134f5458c11a30a1
+size 989890712

model-00009-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec203f5296b76bc93c6ae043e655cee0e6c12b9ab06f5d506bb01b893fe3f40
+size 989907328

model-00010-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26ad01fc048ab8941f0249844c842fb36b1582ef2aaa9c92694a3fa100ffc3dc
+size 956336632

model-00011-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4dc1794b4ffe21920e897b0e37d0229d88da15351a85067a29d41619bff5f2c
+size 989890720

model-00012-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac08812c0c9c8d4fc5dddb33a8b4c64432ffa9c9c3d0dacbd8c5b4bfb5001db9
+size 989890712

model-00013-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9acb980c09d7a1c9503e2faf0e3655c18748873ff2d745ed4067c0de62685a4c
+size 989907328

model-00014-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6655a47df15aa6ea4862ad3b0d73c0356bbf521c50230d8ced779e83fd6de67c
+size 956336632

model-00015-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:916ead36fbbe5a3353b43697aa87aedbeb110dcb07a864ca0abf96e9a9dc0916
+size 989890720

model-00016-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4267da03eee10d738ba0170d9c2cde535fcb8a639379b08c06e3aeca9473681
+size 234906168

model-00017-of-00017.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674610adfedb7f19d21475a7280d6b34774894e654f1d50f4c24444ba7bd0d04
+size 1050673280

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00017-of-00017.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00017.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00017.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00017.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00017.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00017.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00017.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00017.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00017.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00017.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00017.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00016-of-00017.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00017.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00017.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00017.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00017.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00017.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00017.safetensors",
+    "model.norm.weight": "model-00016-of-00017.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}