Spaces:
Paused
Paused
Commit History
-
Fix CUDA device-side assert by adjusting max_prompt_length and disabling use_cache
mayank1365fe123ff -
Fix IndentationError and duplicate reward logic
mayank13650d40379 -
Fix dtype mismatch in training and update blog
mayank1365463c260 -
fix: resolve tensor size mismatch in reward_function by indexing correctly
mayank1365134ff83 -
fix: resolve Gradio JSON error by passing dicts directly instead of serialized strings
mayank1365731ed55 -
fix: resolve 422 errors by sanitizing JSON and fix python syntax error
mayank1365117c380 -
fix: explicitly add unsloth_zoo to requirements to resolve ImportError
mayank1365f8ddd90 -
fix: unpin torch and use simpler unsloth install to resolve HF build cache miss
mayank1365091e56d -
fix: downgrade CUDA to 12.1 and pin torch versions for HF Space compatibility
mayank1365723a53e -
fix: improve GRPO learning signal and handle 422 environment errors
mayank1365f5df9dc -
feat: randomize number of facts (2-4) per episode for better training diversity
mayank1365b676c5d -
fix: address reward plateau by adding format rewards and improving GRPO logic
mayank1365b588360 -
fix: resolve GPU detection issue on HF Spaces
mayank1365ef2c4bf
-
Update app.py
Verified signature69d4d30 -
Update requirements.txt
Verified signatureb8fb5aa -
Update requirements.txt
Verified signature392faa7 -
Update requirements.txt
Verified signatureb4a6032 -
Update requirements.txt
Verified signature47363ae -
Create requirements.txt
Verified signaturedad4e20 -
Rename ap.py to app.py
Verified signature01057a2 -
Rename train_suspect_x.py to ap.py
Verified signature021896a -
Upload train_suspect_x.py with huggingface_hub
Verified signature0355697 -
initial commit
Verified signature1d47818