Spaces:
Sleeping
Sleeping
Commit History
-
Add GPU/unsloth support and local scientist runtime for HF Spaces
- Load LoRA model from SCIENTIST_HF_MODEL env var (HF Hub ID) - Add 'local' runtime that uses fine-tuned model for /agent-step - Install torch (CUDA 12.1) + unsloth + peft in Dockerfile Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>c783c53 -
Initial HF Spaces deployment
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>80d8c84