Robotics
Transformers
Safetensors
qwen3_vl
image-text-to-text
vision-language
vla
qwen3-vl
starvla
fast-tokens
Instructions to use LinhanWang/Qwen3-VL-2B-Instruct-Action with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LinhanWang/Qwen3-VL-2B-Instruct-Action with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("LinhanWang/Qwen3-VL-2B-Instruct-Action") model = AutoModelForImageTextToText.from_pretrained("LinhanWang/Qwen3-VL-2B-Instruct-Action") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 4b0c22963088c40e76cb311631910e47669b0ad1e684776e98445a8f3f01f4b8
- Size of remote file:
- 11.8 MB
- SHA256:
- b9e17876e8019c6a11689cd8f236b1c2a6b31fc6eb7c635a29e80ceffbe5eb68
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.