Spaces:
Sleeping
Sleeping
Commit History
-
Add Ollama fallback support to ai_fixer
havinashpatil05d943b -
Add Hugging Face Inference API fallback for AI fixer
havinashpatil18261cc -
Fix builtin syntax fixer for inline one-line headers and validate TGI fixes
havinashpatil0c0a8ff -
Fix TGI endpoint plumbing and use full TGI runtime image in Dockerfile
havinashpatila8bc575 -
Add TGI integration for cloud LLM serving
havinashpatil- Update ai_fixer.py to use TGI instead of Ollama - Modify Dockerfile for multi-stage build with TGI - Update FastAPI /fix endpoint to use TGI parameters - Update README with TGI documentation and model lists - Enable production LLM serving on HF Spaces434afdf -
Serve React frontend from FastAPI backend for one-click access
havinashpatil62c7e95 -
Finalizing CodeArena RL Benchmark: frontend improvements, GRPO training scripts, and cleaned environment
havinashpatil03a7eb9
-
Complete all tasks: Adaptive curriculum, GRPO, React frontend, LLM-as-a-judge
havinashpatila448db8 -
Upload meta
havinashpatil03defc2
-
fix: reset task_id parsing, grader tuple crash fallback, and inference score output
646409d -
fix: clamp scores to strict (0.001, 0.999) range
b3485c6 -
fix: openenv.yaml tasks graders + strict score bounds
9967cb5 -
fix: add safe_reward() clamp at every reward return point
f14f8d9 -
Add normalize_reward(); enforce strict (0,1) on all paths
b53855f -
Update grading logic to strict (0,1) ratio fallback
78b7e6b -
fix: OpenEnv multi-mode compliance — add main() entrypoint and uv.lock
e92bfc1 -
Production-ready: add server/app.py with fallback-safe /reset, fix Dockerfile, add HF metadata, add task JSON files
dcc8fa3 -
Initial commit
54a19c9