初始化项目,由ModelHub XC社区提供模型

Model: TigerResearch/tigerbot-13b-chat-v2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-28 08:43:03 +08:00
commit 0dd58bbb8a
13 changed files with 148147 additions and 0 deletions

35
.gitattributes vendored Normal file
View File

@@ -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

25
README.md Normal file
View File

@@ -0,0 +1,25 @@
---
license: apache-2.0
language:
- zh
- en
---
<div style="width: 100%;">
<img src="http://x-pai.algolet.com/bot/img/logo_core.png" alt="TigerBot" style="width: 20%; display: block; margin: auto;">
</div>
<p align="center">
<font face="黑体" size=5"> A cutting-edge foundation for your very own LLM. </font>
</p>
<p align="center">
🌐 <a href="https://tigerbot.com/" target="_blank">TigerBot</a> • 🤗 <a href="https://huggingface.co/TigerResearch" target="_blank">Hugging Face</a>
</p>
## Github
https://github.com/TigerResearch/TigerBot
## Usage
配合Github repo中的`infer.py`使用:
```shell
python infer.py --model_path TigerResearch/tigerbot-13b-chat-v2
```

5
added_tokens.json Normal file
View File

@@ -0,0 +1,5 @@
{
"\n\n### Instruction:\n": 60512,
"\n\n### Response:\n": 60513,
"<pad>": 60514
}

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "/mnt/nfs/yechen/models/tigerbot-13b-2h-sft-20g-mix0.0-group/",
"architectures": [
"LlamaForCausalLM"
],
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 13824,
"max_position_embeddings": 2048,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 40,
"pad_token_id": 0,
"pretraining_tp": 8,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.31.0",
"use_cache": true,
"vocab_size": 60928
}

9
generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"do_sample": true,
"eos_token_id": 2,
"max_length": 1024,
"pad_token_id": 60514,
"repetition_penalty": 1.1,
"temperature": 0.3,
"transformers_version": "4.31.0"
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:55c8bc8d21e32f468cd6b4fea23089fee9dcdda75d108afaf287ddf835a80563
size 9998513639

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:251d275e4d3d22770f60adc6f36b6405dcad3b10090af8950296266a06fd46bb
size 9867486361

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fc9690ff126e1ceb87018846f221124167eb54c412ddac549b61fb33041e40ce
size 6758322601

View File

@@ -0,0 +1,410 @@
{
"metadata": {
"total_size": 26624184320
},
"weight_map": {
"lm_head.weight": "pytorch_model-00003-of-00003.bin",
"model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00003.bin",
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
"model.norm.weight": "pytorch_model-00003-of-00003.bin"
}
}

28
special_tokens_map.json Normal file
View File

@@ -0,0 +1,28 @@
{
"additional_special_tokens": [
"\n\n### Instruction:\n",
"\n\n### Response:\n"
],
"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": "<pad>",
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}

147562
tokenizer.json Normal file

File diff suppressed because it is too large Load Diff

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3197ff342f6cf47c17d8c71bebdd2463aad9a145b78c6310b9841ac690a848b1
size 940840

35
tokenizer_config.json Normal file
View File

@@ -0,0 +1,35 @@
{
"add_bos_token": false,
"add_eos_token": false,
"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
},
"legacy": true,
"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_fast": true
}