From 13ddc8dc583d8b1355909970cb8c27f85b7d3c8b Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Mon, 9 Feb 2026 11:00:39 -0600 Subject: Initial implementation: DAGFormer Phase 1 - olmo_graph.py: Modified OLMo2-1B forward with per-head routing via 256x256 adjacency matrix A - Proportional attribution for post-norm decomposition - All 6 GPU sanity checks pass (baseline diff = 0.000001) - predictor.py: Qwen3-Embedding encoder + MLP decoder + Gumbel-Sigmoid + cascading gate - pipeline.py: End-to-end glue (predictor -> A -> OLMo -> NLL) - trainer.py: Full training loop with DDP, gradient accumulation, eval, checkpointing - dolma.py: Streaming Dolma v1.7 with sequence packing - 43/43 unit tests pass Co-Authored-By: Claude Opus 4.6 --- pyproject.toml | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 pyproject.toml (limited to 'pyproject.toml') diff --git a/pyproject.toml b/pyproject.toml new file mode 100644 index 0000000..d9511ec --- /dev/null +++ b/pyproject.toml @@ -0,0 +1,21 @@ +[project] +name = "dagformer" +version = "0.1.0" +description = "Context-conditioned DAG topology predictor for OLMo2-1B" +requires-python = ">=3.9" +dependencies = [ + "torch>=2.2", + "transformers>=4.40", + "datasets", + "wandb", + "pyyaml", + "einops", +] + +[build-system] +requires = ["setuptools>=64"] +build-backend = "setuptools.backends._legacy:_Backend" + +[tool.setuptools.packages.find] +where = ["."] +include = ["src*"] -- cgit v1.2.3