423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-14 10:56:56 +08:00
Code Issues Packages Projects Releases Wiki Activity

add deepseek moe 236B

Browse Source 
Former-commit-id: 10ab83f4c4
This commit is contained in:
hiyouga
2024-05-08 16:37:54 +08:00
parent e123ec00c5
commit 1d3fb90590
5 changed files with 12 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
src/llmtuner/extras/constants.py
View File

@@ -324,6 +324,14 @@ register_model_group(
DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-chat",
DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-chat",
},
"DeepSeek-MoE-236B": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2",
},
"DeepSeek-MoE-236B-Chat": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2-Chat",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2-Chat",
},
},
template="deepseek",
)