seconds-0 commited on
Commit
4315b29
·
verified ·
1 Parent(s): b4102e7

Add sponsor acknowledgement

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -38,6 +38,8 @@ model-index:
38
 
39
  **Abstract.** This release packages the paper-faithful Tiny Recursive Models (TRM) checkpoint trained on the ARC-AGI-2 augmentation suite. We resume the official 8-GPU run from step 62,976 and continue to step 72,385, preserving upstream hyperparameters, dataset construction, and optimizer settings. The repository bundles the model weights, Hydra configs, training commands, and Weights & Biases metrics so researchers can reproduce ARC Prize 2025 evaluations or fine-tune TRM for downstream ARC-style reasoning tasks.
40
 
 
 
41
  ## Model Summary
42
  - **Architecture**: Tiny Recursive Model (TRM) with ACT V1 controller
43
  `L_layers=2`, `H_cycles=3`, `L_cycles=4`, hidden size 512, 8 heads, RoPE positional encodings, bfloat16 activations.
 
38
 
39
  **Abstract.** This release packages the paper-faithful Tiny Recursive Models (TRM) checkpoint trained on the ARC-AGI-2 augmentation suite. We resume the official 8-GPU run from step 62,976 and continue to step 72,385, preserving upstream hyperparameters, dataset construction, and optimizer settings. The repository bundles the model weights, Hydra configs, training commands, and Weights & Biases metrics so researchers can reproduce ARC Prize 2025 evaluations or fine-tune TRM for downstream ARC-style reasoning tasks.
40
 
41
+ **Special thanks** to Shawn Lewis (CTO of Weights & Biases) and CoreWeave (coreweave.com) for their extremely generous contribution of 2×8×H200 GPU-hours through the CoreWeave Cloud platform. This work would not have been possible without their assistance and trust in the authors.
42
+
43
  ## Model Summary
44
  - **Architecture**: Tiny Recursive Model (TRM) with ACT V1 controller
45
  `L_layers=2`, `H_cycles=3`, `L_cycles=4`, hidden size 512, 8 heads, RoPE positional encodings, bfloat16 activations.