Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
THU-KEG
/
WildReward-8B
like
3
Follow
Knowledge Engineer Group @ Tsinghua University
112
Text Classification
Transformers
Safetensors
qwen3
reward-model
rlhf
dpo
alignment
wildchat
text-embeddings-inference
arxiv:
2602.08829
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
WildReward-8B
/
training_args.bin
Commit History
Upload training_args.bin
29d270e
verified
Wesleythu
commited on
Dec 29, 2025
Wesleythu commited on
