Update README.md
Browse files
README.md
CHANGED
|
@@ -10,7 +10,7 @@ tags:
|
|
| 10 |
|
| 11 |
Bagel-Robotics-1 combines task-critical data selection, adaptive structured pruning and recovery training to produce a compact world-action model. Its inference pipeline predicts 32 actions, executes 16 before replanning, and applies 90/10 temporal ensembling. VPP2 is used only as the base model for validation; the training and inference recipe is specific to Bagel-Robotics-1.
|
| 12 |
|
| 13 |
-
|
| 14 |
|
| 15 |
The video expert has **12,468,409,664 parameters**, 23.95% fewer than its recorded parent. Learned masks were converted into smaller FFN and cross-attention layers. Self-attention heads and the action expert are retained. No teacher or learned-mask module is required for inference. Parameter reduction is not a measured inference-speedup claim.
|
| 16 |
|
|
|
|
| 10 |
|
| 11 |
Bagel-Robotics-1 combines task-critical data selection, adaptive structured pruning and recovery training to produce a compact world-action model. Its inference pipeline predicts 32 actions, executes 16 before replanning, and applies 90/10 temporal ensembling. VPP2 is used only as the base model for validation; the training and inference recipe is specific to Bagel-Robotics-1.
|
| 12 |
|
| 13 |
+
**The repository is public and ungated.** Anyone can download the checkpoint and inference files without a Hugging Face account or access token.
|
| 14 |
|
| 15 |
The video expert has **12,468,409,664 parameters**, 23.95% fewer than its recorded parent. Learned masks were converted into smaller FFN and cross-attention layers. Self-attention heads and the action expert are retained. No teacher or learned-mask module is required for inference. Parameter reduction is not a measured inference-speedup claim.
|
| 16 |
|