| [project] | |
| name = "spec-rl" | |
| version = "0.1.5" | |
| description = "HumanEval-style code RL environment whose rollouts are served by the DFlash-speculated Laguna XS.2 vLLM endpoint — same reward curve, cheaper rollouts." | |
| tags = ["code", "humaneval", "single-turn", "rl", "eval", "speculative-decoding", "dflash"] | |
| requires-python = ">=3.11" | |
| dependencies = [ | |
| "verifiers", | |
| "datasets", | |
| ] | |
| [build-system] | |
| requires = ["hatchling"] | |
| build-backend = "hatchling.build" | |
| [tool.hatch.build] | |
| include = ["spec_rl.py", "pyproject.toml", "README.md"] | |
| [tool.verifiers.eval] | |
| num_examples = 20 | |
| rollouts_per_example = 1 | |