Commit History

Drop deprecated TRANSFORMERS_CACHE env var
895724f
verified

anugrah55 commited on

Overhaul trainer: TRL GRPO with env-backed reward, Qwen2.5-0.5B 4bit+LoRA, slim PyTorch CUDA base, heartbeat HTTP for HF Spaces health probe
d597642
verified

anugrah55 commited on

Upload Dockerfile with huggingface_hub
8a53b6a
verified

anugrah55 commited on

Upload Dockerfile with huggingface_hub
a72a735
verified

anugrah55 commited on