Spaces:
Sleeping
Sleeping
Commit History
-
Space T4 + real HF path: split requirements, GPU defaults, API reset behavior
- Add requirements-core.txt for slim Docker; root requirements.txt pulls core + PyTorch/TRL/PEFT for HF GPU Spaces. - README Space frontmatter suggested_hardware t4-small; document secrets FORGE_DETERMINISTIC_RESET and FORGE_DEFAULT_PROVIDER. - config: unset CODE_PROVIDER_MODE defaults to custom_hf when CUDA else offline. - app: GPU-first provider order, default custom_hf on CUDA, higher episode caps on GPU, clearer provider info, fix coach lesson line duplication. - trainer: benchmark respects requested episode count (no forced minimum of 20). - api_server: varied tasks per reset unless FORGE_DETERMINISTIC_RESET=1. - .env.example aligned with GPU Space defaults. Made-with: Cursor49a72d3 -
Finalize eval-friendly defaults: offline baseline, deterministic API reset, docs cleanup
- Rename user-facing provider mode from mock to offline across README, Docker, Compose, and .env.example; keep silent mock alias in code paths. - POST /reset reseeds RNG from GLOBAL_RANDOM_SEED for reproducible OpenEnv episodes. - MockModelPolicy and router use offline/baseline terminology in metadata; remove tracked coach_memory.json.tmp and ignore *.tmp. - Gradio defaults to offline provider; trainer and sample outputs use baseline:model:* labels. Made-with: Cursor0c741d9 -
fix(api): Pydantic v2 step payload (exclude_none); env candidate_solutions; README Space API curl guide; Gradio API tab
Made-with: Cursor2b35bd5 -
fix(space): fastapi>=0.115.2 for Gradio 5.25; Pydantic v2 model_dump in API
Made-with: Cursor4b17fa3 -
Final hardening for 100% submission readiness
c2975af
-
Final cleanup for FORGE-v4: Colab entrypoint, OpenEnv API, 10x optimization, and Judge Narrative generation
3978c05