Update special_tokens_map.json
This commit is contained in:
ai-modelscope
32
.gitattributes
vendored
32
.gitattributes
vendored
@@ -1,47 +1,37 @@
|
|||||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
*.arrow 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
|
||||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.bz2 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
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
*.lfs.* 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
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
*.msgpack 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
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pb 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
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
*.rar 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
|
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
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
*.tgz 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
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
*.zip 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
|
|
||||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
|
||||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
pytorch_model-00001-of-00002.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
pytorch_model-00002-of-00002.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
|||||||
105
README.md
105
README.md
@@ -1,47 +1,70 @@
|
|||||||
---
|
---
|
||||||
license: Apache License 2.0
|
inference: false
|
||||||
|
license: other
|
||||||
#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
|
<!-- header start -->
|
||||||
```bash
|
<div style="width: 100%;">
|
||||||
#安装ModelScope
|
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
|
||||||
pip install modelscope
|
</div>
|
||||||
|
<div style="display: flex; justify-content: space-between; width: 100%;">
|
||||||
|
<div style="display: flex; flex-direction: column; align-items: flex-start;">
|
||||||
|
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
|
||||||
|
</div>
|
||||||
|
<div style="display: flex; flex-direction: column; align-items: flex-end;">
|
||||||
|
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
<!-- header end -->
|
||||||
|
|
||||||
|
# OptimalScale's Robin 7B v2 fp16
|
||||||
|
|
||||||
|
These files are pytorch format fp16 model files for [OptimalScale's Robin 7B v2](https://huggingface.co/OptimalScale/robin-7b-v2-delta).
|
||||||
|
|
||||||
|
It is the result of merging and/or converting the source repository to float16.
|
||||||
|
|
||||||
|
## Repositories available
|
||||||
|
|
||||||
|
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/robin-7B-v2-GPTQ)
|
||||||
|
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/robin-7B-v2-GGML)
|
||||||
|
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/robin-7B-v2-fp16)
|
||||||
|
|
||||||
|
## Prompt template
|
||||||
|
|
||||||
```
|
```
|
||||||
```python
|
A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions
|
||||||
#SDK模型下载
|
###Human: prompt
|
||||||
from modelscope import snapshot_download
|
###Assistant:
|
||||||
model_dir = snapshot_download('TheBloke/robin-7B-v2-fp16')
|
|
||||||
```
|
|
||||||
Git下载
|
|
||||||
```
|
|
||||||
#Git模型下载
|
|
||||||
git clone https://www.modelscope.cn/TheBloke/robin-7B-v2-fp16.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>
|
<!-- footer start -->
|
||||||
|
## Discord
|
||||||
|
|
||||||
|
For further support, and discussions on these models and AI in general, join us at:
|
||||||
|
|
||||||
|
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
|
||||||
|
|
||||||
|
## Thanks, and how to contribute.
|
||||||
|
|
||||||
|
Thanks to the [chirper.ai](https://chirper.ai) team!
|
||||||
|
|
||||||
|
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
|
||||||
|
|
||||||
|
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
|
||||||
|
|
||||||
|
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
|
||||||
|
|
||||||
|
* Patreon: https://patreon.com/TheBlokeAI
|
||||||
|
* Ko-Fi: https://ko-fi.com/TheBlokeAI
|
||||||
|
|
||||||
|
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
|
||||||
|
|
||||||
|
**Patreon special mentions**: vamX, K, Jonathan Leane, Lone Striker, Sean Connelly, Chris McCloskey, WelcomeToTheClub, Nikolai Manek, John Detwiler, Kalila, David Flickinger, Fen Risland, subjectnull, Johann-Peter Hartmann, Talal Aujan, John Villwock, senxiiz, Khalefa Al-Ahmad, Kevin Schuppel, Alps Aficionado, Derek Yates, Mano Prime, Nathan LeClaire, biorpg, trip7s trip, Asp the Wyvern, chris gileta, Iucharbius , Artur Olbinski, Ai Maven, Joseph William Delisle, Luke Pendergrass, Illia Dulskyi, Eugene Pentland, Ajan Kanaga, Willem Michiel, Space Cruiser, Pyrater, Preetika Verma, Junyu Yang, Oscar Rangel, Spiking Neurons AB, Pierre Kircher, webtim, Cory Kujawski, terasurfer , Trenton Dambrowitz, Gabriel Puliatti, Imad Khwaja, Luke.
|
||||||
|
|
||||||
|
Thank you to all my generous patrons and donaters!
|
||||||
|
|
||||||
|
<!-- footer end -->
|
||||||
|
|
||||||
|
# Original model card: OptimalScale's Robin 7B v2
|
||||||
|
|
||||||
|
No model card provided in source repository.
|
||||||
|
|||||||
24
config.json
Normal file
24
config.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "/workspace/process/lora_base/huggyllama_llama-7b",
|
||||||
|
"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,
|
||||||
|
"max_sequence_length": 2048,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 32,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.30.0.dev0",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 32000
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"transformers_version": "4.30.0.dev0"
|
||||||
|
}
|
||||||
3
pytorch_model-00001-of-00002.bin
Normal file
3
pytorch_model-00001-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:53d136c94671b3908ccd8655f2901fdcc3ba26aa733fe3add3798c081db8555b
|
||||||
|
size 9976634558
|
||||||
3
pytorch_model-00002-of-00002.bin
Normal file
3
pytorch_model-00002-of-00002.bin
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:64d9e49a8d66f11456298fbd0d99fa1eb5628b402f586d6b456435de759b0c84
|
||||||
|
size 3500315539
|
||||||
330
pytorch_model.bin.index.json
Normal file
330
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,330 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 13476839424
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
||||||
|
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
||||||
|
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
||||||
|
}
|
||||||
|
}
|
||||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -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
|
||||||
|
}
|
||||||
|
}
|
||||||
93391
tokenizer.json
Normal file
93391
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||||
|
size 499723
|
||||||
33
tokenizer_config.json
Normal file
33
tokenizer_config.json
Normal file
@@ -0,0 +1,33 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": true,
|
||||||
|
"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
|
||||||
|
},
|
||||||
|
"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
|
||||||
|
}
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user