| # ── Core environment runtime ──────────────────────────────────────────────── | |
| pydantic>=2.0 | |
| numpy>=1.24 | |
| # ── HTTP server (Hugging Face Space, OpenEnv contract) ────────────────────── | |
| fastapi>=0.100.0 | |
| uvicorn>=0.23.0 | |
| python-multipart>=0.0.6 | |
| # ── LLM client (used by inference.py for OpenAI-compatible API rollouts) ──── | |
| openai>=1.0 | |
| # ── Replay rendering / dashboards ─────────────────────────────────────────── | |
| matplotlib>=3.7 | |
| imageio>=2.28 | |
| Pillow>=9.0 | |
| # ── Test suite ────────────────────────────────────────────────────────────── | |
| pytest>=7.0 | |
| pytest-cov>=4.0 | |
| # ── Optional extras for evaluating a trained adapter locally ──────────────── | |
| # (Training itself is run on Colab/HF Space JupyterLab; see training/grpo_v2_colab.ipynb, | |
| # which installs unsloth + trl + datasets inline. These pins here are purely so | |
| # `python scripts/eval_trained_model.py` works in a stock Python venv.) | |
| # torch>=2.1 | |
| # transformers>=4.45 | |
| # accelerate>=0.30 | |
| # peft>=0.10 | |
| # safetensors>=0.4 | |