Robotics
Transformers
Safetensors
qwen2_5_vl
image-text-to-text
vision-language-action-model
vision-language-model
text-generation-inference
Instructions to use InternRobotics/InternVLA-M1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use InternRobotics/InternVLA-M1 with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("InternRobotics/InternVLA-M1") model = AutoModelForImageTextToText.from_pretrained("InternRobotics/InternVLA-M1") - Notebooks
- Google Colab
- Kaggle
Spatial Grounding Pipeline
#3
by Jarry2020 - opened
Hi, Do you have any plans uploading vlm data or spatial grounding pretrain pipeline?
Jarry2020 changed discussion title from Spatial Grounding Pre-training included? to Spatial Grounding Pipeline