423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-23 22:32:54 +08:00
Code Issues Packages Projects Releases Wiki Activity

add deepseek3 model

Browse Source 
Former-commit-id: e67b9dcc3ad0c003bc3afd7601ecd2adfbf9666b
This commit is contained in:
hiyouga 2024-12-30 13:38:30 +00:00
parent 1178cb0e33
commit d0e729cd33
4 changed files with 32 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@ -191,6 +191,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 | | [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 |
| [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere | | [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere |
| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek | | [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek |
| [DeepSeek 2.5/3](https://huggingface.co/deepseek-ai) | 236B/685B | deepseek3 |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon | | [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma | | [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 | | [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 |

1
README_zh.md
View File

@ -192,6 +192,7 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
| [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 | | [ChatGLM3](https://huggingface.co/THUDM) | 6B | chatglm3 |
| [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere | | [Command R](https://huggingface.co/CohereForAI) | 35B/104B | cohere |
| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek | | [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai) | 7B/16B/67B/236B | deepseek |
| [DeepSeek 2.5/3](https://huggingface.co/deepseek-ai) | 236B/685B | deepseek3 |
| [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon | | [Falcon](https://huggingface.co/tiiuae) | 7B/11B/40B/180B | falcon |
| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma | | [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google) | 2B/7B/9B/27B | gemma |
| [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 | | [GLM-4](https://huggingface.co/THUDM) | 9B | glm4 |

3
src/llamafactory/data/template.py
View File

@ -619,9 +619,8 @@ _register_template(
_register_template( _register_template(
name="deepseek_v2.5", name="deepseek3",
format_user=StringFormatter(slots=["<｜User｜>{{content}}<｜Assistant｜>"]), format_user=StringFormatter(slots=["<｜User｜>{{content}}<｜Assistant｜>"]),
format_system=StringFormatter(slots=["{{content}}"]),
format_prefix=EmptyFormatter(slots=[{"bos_token"}]), format_prefix=EmptyFormatter(slots=[{"bos_token"}]),
) )

29
src/llamafactory/extras/constants.py
View File

@ -448,6 +448,7 @@ register_model_group(
}, },
"DeepSeek-Coder-7B-Base": { "DeepSeek-Coder-7B-Base": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-7b-base-v1.5", DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-7b-base-v1.5",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-coder-7b-base-v1.5",
}, },
"DeepSeek-Coder-33B-Base": { "DeepSeek-Coder-33B-Base": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-33b-base", DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-33b-base",
@ -459,6 +460,7 @@ register_model_group(
}, },
"DeepSeek-Coder-7B-Instruct": { "DeepSeek-Coder-7B-Instruct": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-7b-instruct-v1.5", DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
}, },
"DeepSeek-Coder-33B-Instruct": { "DeepSeek-Coder-33B-Instruct": {
DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-33b-instruct", DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-33b-instruct",
@ -469,6 +471,33 @@ register_model_group(
) )
register_model_group(
models={
"DeepSeek-V2-236B-Chat-0628": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2-Chat-0628",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2-Chat-0628",
},
"DeepSeek-V2.5-236B-Chat": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2.5",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2.5",
},
"DeepSeek-V2.5-236B-Chat-1210": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2.5-1210",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2.5-1210",
},
"DeepSeek-V3-685B-Base": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V3-Base",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V3-Base",
},
"DeepSeek-V3-685B-Chat": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V3",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V3",
},
},
template="deepseek3",
)
register_model_group( register_model_group(
models={ models={
"EXAONE-3.0-7.8B-Instruct": { "EXAONE-3.0-7.8B-Instruct": {