xinyun/DeepSeek-R1-Distill-Qwen-32B
1
0
Fork 0
mirror of https://www.modelscope.cn/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B.git synced 2025-12-08 20:44:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add generation_config.json

Browse Source
This commit is contained in:
ai-modelscope 2025-01-21 20:25:22 +08:00
parent 6166147947
commit aa6e681058
3 changed files with 13 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
.gitattributes vendored
View File

@ -33,11 +33,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
model-00001-of-000008.safetensors filter=lfs diff=lfs merge=lfs -text
model-00002-of-000008.safetensors filter=lfs diff=lfs merge=lfs -text
model-00003-of-000008.safetensors filter=lfs diff=lfs merge=lfs -text
model-00004-of-000008.safetensors filter=lfs diff=lfs merge=lfs -text
model-00005-of-000008.safetensors filter=lfs diff=lfs merge=lfs -text
model-00006-of-000008.safetensors filter=lfs diff=lfs merge=lfs -text
model-00007-of-000008.safetensors filter=lfs diff=lfs merge=lfs -text
model-00008-of-000008.safetensors filter=lfs diff=lfs merge=lfs -text

5
README.md
View File

@ -1,3 +1,6 @@
---
library_name: transformers
---
# DeepSeek-R1
<!-- markdownlint-disable first-line-h1 -->
<!-- markdownlint-disable html -->
@ -206,4 +209,4 @@ DeepSeek-R1 series support commercial use, allow for any modifications and deriv
```
## 9. Contact
If you have any questions, please raise an issue or contact us at [service@deepseek.com](service@deepseek.com).
If you have any questions, please raise an issue or contact us at [service@deepseek.com](service@deepseek.com).

9
generation_config.json Normal file
View File

@ -0,0 +1,9 @@
{
"_from_model_config": true,
"bos_token_id": 151646,
"eos_token_id": 151643,
"do_sample": true,
"temperature": 0.6,
"top_p": 0.95,
"transformers_version": "4.39.3"
}