Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
alothomas
/
Qwen2.5-0.5B-PRM-RAD-balanced-150k-LastStepOnly
like
0
Token Classification
Transformers
Safetensors
qwen2
Generated from Trainer
prm
trl
text-generation-inference
arxiv:
2211.14275
Model card
Files
Files and versions
xet
Community
Deploy
Use this model
main
Qwen2.5-0.5B-PRM-RAD-balanced-150k-LastStepOnly
Commit History
Upload eval/predictions.csv with huggingface_hub
d451153
verified
alothomas
commited on
Sep 24, 2025
Training in progress, step 500
c835ebe
verified
alothomas
commited on
Sep 24, 2025
initial commit
62b0047
verified
alothomas
commited on
Sep 24, 2025
alothomas
commited on
