setup

pyproject.toml

@@ -0,0 +1,40 @@
+[project]
+name = "projected_grpo"
+version = "0.1.0"
+description = "SVD-basis gradient projection vs RL reward hacking on Nanda's LeetCode benchmark"
+requires-python = ">=3.11"
+dependencies = [
+    "torch>=2.4",
+    "transformers>=4.45",
+    "einops>=0.8",
+    "jaxtyping>=0.2",
+    "beartype>=0.18",
+    "loguru>=0.7",
+    "polars>=1.0",
+    "tabulate>=0.9",
+    "tyro>=0.8",
+    "tqdm>=4.66",
+    "numpy<2.0",
+    "datasets>=3.0",
+    "huggingface_hub>=0.24",
+    "wandb>=0.18",
+    "peft>=0.13",
+]
+
+[project.optional-dependencies]
+gpu = [
+    "vllm>=0.10",
+]
+
+[tool.ruff.lint]
+ignore = ["F722"]  # jaxtyping shape strings
+
+[build-system]
+requires = ["setuptools>=68"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.uv]
+exclude-newer = "2026-05-23"