Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
WisdomShell
/
RewardAnything-8B-v1
like
22
Follow
WisdomShell
21
Text Generation
Safetensors
English
Chinese
qwen3
reward-model
rlhf
principle-following
qwen
conversational
arxiv:
2506.03637
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
3
Deploy
Use this model
cf76a98
RewardAnything-8B-v1
/
generation_config.json
Commit History
Duplicate from zhuohaoyu/RewardAnything-8B-v1
243e876
verified
zhuohaoyu
commited on
Jun 4
zhuohaoyu
commited on
