Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
McClain
/
grpo-6000
like
0
Safetensors
gpt2
Model card
Files
Files and versions
xet
Community
main
grpo-6000
/
tokenizer.json
Commit History
Convert VERL/GRPO actor checkpoint to HF format
c6f4c30
verified
McClain
commited on
Oct 20, 2025