Hugging Face's logo

laion
/
rl_r2egym-nl2bash-stack-bugsseq-fixthink-again_lr1e-5_pr

Safetensors
qwen3
Model card Files
xet
 Community
rl_r2egym-nl2bash-stack-bugsseq-fixthink-again_lr1e-5_pr / tokenizer.json

Commit History

Run 28: PR dataset, lr=1e-5, step 5 checkpoint (fixthink-again base)
673c9f4
verified

EtashGuha commited on