From 66e0d8b9fd4d0f7a2231d689c055e26fdf1cf04a Mon Sep 17 00:00:00 2001 From: YurenHao0426 Date: Sat, 13 Jun 2026 12:35:36 -0500 Subject: rrm workspace: TRM/HRM/SRM code, Maze dataset, dynamical-analysis pipeline Curated export for clone-and-run Maze training (2x A6000) + diagnostics. trm/hrm pretrain.py carry trajectory-augmentation code (backward-compatible). Heavy artifacts (checkpoints/wandb/npz) gitignored; see PROVENANCE.md. Co-Authored-By: Claude Fable 5 --- srm/config/arch/hrm_v1.yaml | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) create mode 100644 srm/config/arch/hrm_v1.yaml (limited to 'srm/config/arch/hrm_v1.yaml') diff --git a/srm/config/arch/hrm_v1.yaml b/srm/config/arch/hrm_v1.yaml new file mode 100644 index 0000000..a5646b8 --- /dev/null +++ b/srm/config/arch/hrm_v1.yaml @@ -0,0 +1,21 @@ +name: hrm.hrm_act_v1@HierarchicalReasoningModel_ACTV1 +loss: + name: losses@ACTLossHead + loss_type: stablemax_cross_entropy + +halt_exploration_prob: 0.1 +halt_max_steps: 16 + +H_cycles: 2 +L_cycles: 2 + +H_layers: 4 +L_layers: 4 + +hidden_size: 512 +num_heads: 8 # min(2, hidden_size // 64) +expansion: 4 + +puzzle_emb_ndim: ${.hidden_size} + +pos_encodings: rope -- cgit v1.2.3