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 --- src/__init__.py | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 src/__init__.py (limited to 'src/__init__.py') diff --git a/src/__init__.py b/src/__init__.py new file mode 100644 index 0000000..e69de29 -- cgit v1.2.3