Update README.md
Browse files
README.md
CHANGED
|
@@ -3,7 +3,7 @@ base_model:
|
|
| 3 |
- sapientinc/HRM-checkpoint-ARC-2
|
| 4 |
- sapientinc/HRM-checkpoint-sudoku-extreme
|
| 5 |
- sapientinc/HRM-checkpoint-maze-30x30-hard
|
| 6 |
-
-
|
| 7 |
---
|
| 8 |
|
| 9 |
HRM-LLM: A truly decentralized, human-like reasoning model built by the community
|
|
@@ -36,8 +36,4 @@ Jump in and train
|
|
| 36 |
Quick start: contribute training from your environment
|
| 37 |
Run this to join training and push your contribution to the shared checkpoint.
|
| 38 |
|
| 39 |
-
That’s it—share the Colab link, invite contributors, and let the community grow HRM-LLM together.
|
| 40 |
-
# HRM Community Model
|
| 41 |
-
|
| 42 |
-
Epoch: 7
|
| 43 |
-
Validation Loss: 6.5961
|
|
|
|
| 3 |
- sapientinc/HRM-checkpoint-ARC-2
|
| 4 |
- sapientinc/HRM-checkpoint-sudoku-extreme
|
| 5 |
- sapientinc/HRM-checkpoint-maze-30x30-hard
|
| 6 |
+
- google/flan-t5-small
|
| 7 |
---
|
| 8 |
|
| 9 |
HRM-LLM: A truly decentralized, human-like reasoning model built by the community
|
|
|
|
| 36 |
Quick start: contribute training from your environment
|
| 37 |
Run this to join training and push your contribution to the shared checkpoint.
|
| 38 |
|
| 39 |
+
That’s it—share the Colab link, invite contributors, and let the community grow HRM-LLM together.
|
|
|
|
|
|
|
|
|
|
|
|