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

[model] add deepseek-R1 & show think process (#6767)

Browse Source 
Former-commit-id: 4dccb724af51208a001c96fefbdbf226be09e50c
This commit is contained in:
qvlehao
2025-01-29 12:16:26 +08:00
committed by GitHub
parent a8fae3869d
commit 4f298894da
4 changed files with 35 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
src/llamafactory/extras/constants.py
View File

@@ -493,6 +493,38 @@ register_model_group(
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V3",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V3",
},
"DeepSeek-R1-1.5B-Distill": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B",
},
"DeepSeek-R1-7B-Distill": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B",
},
"DeepSeek-R1-8B-Distill": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
},
"DeepSeek-R1-14B-Distill": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
},
"DeepSeek-R1-32B-Distill": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
},
"DeepSeek-R1-70B-Distill": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
},
"DeepSeek-R1-671B-Zero": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-R1-Zero",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-R1-Zero",
},
"DeepSeek-R1-671B": {
DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-R1",
DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-R1",
},
},
template="deepseek3",
)

1
src/llamafactory/webui/chatter.py
View File

@@ -157,6 +157,7 @@ class WebChatModel(ChatModel):
top_p=top_p,
temperature=temperature,
):
new_text = '' if any(t in new_text for t in ('<think>', '</think>')) else new_text
response += new_text
if tools:
result = self.engine.template.extract_tool(response)