Spaces:

anugrah55
/

opensleuth-training-gemini-cli

Paused

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 13 days ago

11.7 kB

This file contains binary data. It cannot be displayed, but you can still download it.