Robotics
Transformers
Safetensors
xvla
feature-extraction
vla
vision-language-action
flow-matching
x-vla
so101
multitask
custom_code
Instructions to use twanghcmut/X-VLA-SO101-LeftArm-Multitask with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use twanghcmut/X-VLA-SO101-LeftArm-Multitask with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("twanghcmut/X-VLA-SO101-LeftArm-Multitask", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
X-VLA-Pt fine-tuned on hungho77/so101-left-arm-multitask (24000 iters, batch 16 x 2)
66b1c35 verified Download preprocessor_config.json from twanghcmut/X-VLA-SO101-LeftArm-Multitask: direct link, hf CLI and curl.
- Browser
- Download file 561 Bytes
-
https://huggingface.co/twanghcmut/X-VLA-SO101-LeftArm-Multitask/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://twanghcmut/X-VLA-SO101-LeftArm-Multitask/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/twanghcmut/X-VLA-SO101-LeftArm-Multitask/resolve/main/preprocessor_config.json
561 Bytes
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_xvla.XVLAProcessor" | |
| }, | |
| "crop_size": { | |
| "height": 224, | |
| "width": 224 | |
| }, | |
| "do_center_crop": false, | |
| "do_convert_rgb": null, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "CLIPImageProcessor", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "processor_class": "XVLAProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 224, | |
| "width": 224 | |
| } | |
| } | |