p04798526
/
LLaMA-Factory-Mirror
1
0
Fork 1
Code Issues Pull Requests Packages Projects Releases Wiki Activity

add qwen2 math models

This commit is contained in:
hiyouga 2024-08-09 20:20:35 +08:00
parent 0a690ada6f
commit dc770efb14
3 changed files with 78 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -154,7 +154,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
## Supported Models
| Model | Model size | Template |
| ------------------------------------------------------------ | -------------------------------- | --------- |
| ----------------------------------------------------------------- | -------------------------------- | --------- |
| [Baichuan 2](https://huggingface.co/baichuan-inc) | 7B/13B | baichuan2 |
| [BLOOM/BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | - |
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 |
@ -174,7 +174,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
| [PaliGemma](https://huggingface.co/google) | 3B | gemma |
| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - |
| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi |
| [Qwen/Qwen1.5/Qwen2 (Code/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen |
| [Qwen/Qwen1.5/Qwen2 (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen |
| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - |
| [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse |
| [Yi/Yi-1.5](https://huggingface.co/01-ai) | 6B/9B/34B | yi |

4
README_zh.md
View File

@ -154,7 +154,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
## 模型
| 模型名 | 模型大小 | Template |
| ------------------------------------------------------------ | -------------------------------- | --------- |
| ----------------------------------------------------------------- | -------------------------------- | --------- |
| [Baichuan 2](https://huggingface.co/baichuan-inc) | 7B/13B | baichuan2 |
| [BLOOM/BLOOMZ](https://huggingface.co/bigscience) | 560M/1.1B/1.7B/3B/7.1B/176B | - |
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 |
@ -174,7 +174,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
| [PaliGemma](https://huggingface.co/google) | 3B | gemma |
| [Phi-1.5/Phi-2](https://huggingface.co/microsoft) | 1.3B/2.7B | - |
| [Phi-3](https://huggingface.co/microsoft) | 4B/7B/14B | phi |
| [Qwen/Qwen1.5/Qwen2 (Code/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen |
| [Qwen/Qwen1.5/Qwen2 (Code/Math/MoE)](https://huggingface.co/Qwen) | 0.5B/1.5B/4B/7B/14B/32B/72B/110B | qwen |
| [StarCoder 2](https://huggingface.co/bigcode) | 3B/7B/15B | - |
| [XVERSE](https://huggingface.co/xverse) | 7B/13B/65B | xverse |
| [Yi/Yi-1.5](https://huggingface.co/01-ai) | 6B/9B/34B | yi |

24
src/llamafactory/extras/constants.py
View File

@ -1244,6 +1244,18 @@ register_model_group(
DownloadSource.DEFAULT: "Qwen/Qwen2-57B-A14B",
DownloadSource.MODELSCOPE: "qwen/Qwen2-57B-A14B",
},
"Qwen2-Math-1.5B": {
DownloadSource.DEFAULT: "Qwen/Qwen2-Math-1.5B",
DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-1.5B",
},
"Qwen2-Math-7B": {
DownloadSource.DEFAULT: "Qwen/Qwen2-Math-7B",
DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-7B",
},
"Qwen2-Math-72B": {
DownloadSource.DEFAULT: "Qwen/Qwen2-Math-72B",
DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-72B",
},
"Qwen2-0.5B-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen2-0.5B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2-0.5B-Instruct",
@ -1264,6 +1276,18 @@ register_model_group(
DownloadSource.DEFAULT: "Qwen/Qwen2-57B-A14B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2-57B-A14B-Instruct",
},
"Qwen2-Math-1.5B-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen2-Math-1.5B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-1.5B-Instruct",
},
"Qwen2-Math-7B-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen2-Math-7B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-7B-Instruct",
},
"Qwen2-Math-72B-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen2-Math-72B-Instruct",
DownloadSource.MODELSCOPE: "qwen/Qwen2-Math-72B-Instruct",
},
"Qwen2-0.5B-int8-Chat": {
DownloadSource.DEFAULT: "Qwen/Qwen2-0.5B-Instruct-GPTQ-Int8",
DownloadSource.MODELSCOPE: "qwen/Qwen2-0.5B-Instruct-GPTQ-Int8",