Add sponsor acknowledgement
Browse files
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.
|