Robotics
Transformers
Safetensors
English
molmoact2
image-text-to-text
OpenRAL
rskill
vision-language-action
nf4
4-bit precision
so100_follower
so101_follower
vla
so101
so100
manipulation
custom_code
8-bit precision
Instructions to use OpenRAL/rskill-molmoact2-multi-so101-nf4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenRAL/rskill-molmoact2-multi-so101-nf4 with Transformers:
# Load model directly from transformers import AutoModelForImageTextToText model = AutoModelForImageTextToText.from_pretrained("OpenRAL/rskill-molmoact2-multi-so101-nf4", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
chore: canonical naming migration
Browse files
SKILL.md
CHANGED
|
@@ -5,7 +5,7 @@ description: >-
|
|
| 5 |
metadata:
|
| 6 |
openral_rskill: true # generated discovery view of an rSkill
|
| 7 |
schema_version: 0.1
|
| 8 |
-
rskill_id: OpenRAL/rskill-molmoact2-so101-nf4
|
| 9 |
manifest: ./rskill.yaml
|
| 10 |
role: s1
|
| 11 |
kind: vla
|
|
@@ -24,7 +24,7 @@ metadata:
|
|
| 24 |
latency_budget: {per_chunk_ms: 1000.0}
|
| 25 |
license_code: Apache-2.0
|
| 26 |
license_weights: apache-2.0
|
| 27 |
-
weights_uri: hf://OpenRAL/rskill-molmoact2-so101-nf4
|
| 28 |
source_repo: hf://allenai/MolmoAct2-SO100_101
|
| 29 |
paper_url: https://arxiv.org/abs/2605.02881
|
| 30 |
---
|
|
@@ -65,7 +65,7 @@ this file. Execution always goes through the OpenRAL loader and the robot HAL.
|
|
| 65 |
```python
|
| 66 |
from openral_rskill import rSkill
|
| 67 |
|
| 68 |
-
skill = rSkill.from_pretrained("OpenRAL/rskill-molmoact2-so101-nf4")
|
| 69 |
# the loader validates embodiment / sensors / runtime / quantization against the target
|
| 70 |
# RobotDescription and enforces the weight-license gate before any weights load.
|
| 71 |
```
|
|
|
|
| 5 |
metadata:
|
| 6 |
openral_rskill: true # generated discovery view of an rSkill
|
| 7 |
schema_version: 0.1
|
| 8 |
+
rskill_id: OpenRAL/rskill-molmoact2-multi-so101-nf4
|
| 9 |
manifest: ./rskill.yaml
|
| 10 |
role: s1
|
| 11 |
kind: vla
|
|
|
|
| 24 |
latency_budget: {per_chunk_ms: 1000.0}
|
| 25 |
license_code: Apache-2.0
|
| 26 |
license_weights: apache-2.0
|
| 27 |
+
weights_uri: hf://OpenRAL/rskill-molmoact2-multi-so101-nf4
|
| 28 |
source_repo: hf://allenai/MolmoAct2-SO100_101
|
| 29 |
paper_url: https://arxiv.org/abs/2605.02881
|
| 30 |
---
|
|
|
|
| 65 |
```python
|
| 66 |
from openral_rskill import rSkill
|
| 67 |
|
| 68 |
+
skill = rSkill.from_pretrained("OpenRAL/rskill-molmoact2-multi-so101-nf4")
|
| 69 |
# the loader validates embodiment / sensors / runtime / quantization against the target
|
| 70 |
# RobotDescription and enforces the weight-license gate before any weights load.
|
| 71 |
```
|