Update README.md
Browse files
README.md
CHANGED
|
@@ -8,8 +8,6 @@ by Eric Hartford
|
|
| 8 |
I love GR00T but NVidia's license - Tsk-tsk, no no no, that won't do at all.
|
| 9 |
Also all their inference code is wrapped in hard coded CUDA dependencies. Rude.
|
| 10 |
|
| 11 |
-
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/SJo_YZmamnVRoBI4lMCoC.png" width="600" />
|
| 12 |
-
|
| 13 |
The world - our future - and our children's future - deserves a high quality permissively licensed robot control model that isn't tied to any specific hardware.
|
| 14 |
|
| 15 |
This repo contains a fully open-source Apache 2.0 licensed, randomly initialized version of the GR00T-N1.5-3B architecture for humanoid robot control. This model has the exact same architecture as NVIDIA's GR00T-N1.5-3B but with random weights.
|
|
@@ -25,6 +23,8 @@ The whole job looks like this:
|
|
| 25 |
3) missing components - find some initialization that's better than "random" - like merging from similar models into the correct shape.
|
| 26 |
4) distill GR00T onto it with online logit distillation. The model's small, easy to load both models into vram!
|
| 27 |
|
|
|
|
|
|
|
| 28 |
## Model Description
|
| 29 |
|
| 30 |
DolphinGR00T-N1.5-3B-Zero is a Vision-Language-Action (VLA) model designed for humanoid robot control:
|
|
|
|
| 8 |
I love GR00T but NVidia's license - Tsk-tsk, no no no, that won't do at all.
|
| 9 |
Also all their inference code is wrapped in hard coded CUDA dependencies. Rude.
|
| 10 |
|
|
|
|
|
|
|
| 11 |
The world - our future - and our children's future - deserves a high quality permissively licensed robot control model that isn't tied to any specific hardware.
|
| 12 |
|
| 13 |
This repo contains a fully open-source Apache 2.0 licensed, randomly initialized version of the GR00T-N1.5-3B architecture for humanoid robot control. This model has the exact same architecture as NVIDIA's GR00T-N1.5-3B but with random weights.
|
|
|
|
| 23 |
3) missing components - find some initialization that's better than "random" - like merging from similar models into the correct shape.
|
| 24 |
4) distill GR00T onto it with online logit distillation. The model's small, easy to load both models into vram!
|
| 25 |
|
| 26 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/63111b2d88942700629f5771/SJo_YZmamnVRoBI4lMCoC.png" width="600" />
|
| 27 |
+
|
| 28 |
## Model Description
|
| 29 |
|
| 30 |
DolphinGR00T-N1.5-3B-Zero is a Vision-Language-Action (VLA) model designed for humanoid robot control:
|