Robotics
Transformers
Safetensors
qwen3_vl
image-text-to-text
embodied-navigation
vision-language-navigation
visual-tracking
vision-language-action
qwen3-vl
Instructions to use LightOriginsHQ/LightNav-0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use LightOriginsHQ/LightNav-0 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("LightOriginsHQ/LightNav-0") model = AutoModelForMultimodalLM.from_pretrained("LightOriginsHQ/LightNav-0", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download action_tokenizer/alpha_per_source.json from LightOriginsHQ/LightNav-0: direct link, hf CLI and curl.
- Browser
- Download file 97 Bytes
-
https://huggingface.co/LightOriginsHQ/LightNav-0/resolve/main/action_tokenizer/alpha_per_source.json
- Command line
-
hf download hf://LightOriginsHQ/LightNav-0/action_tokenizer/alpha_per_source.json
-
curl -L -o alpha_per_source.json https://huggingface.co/LightOriginsHQ/LightNav-0/resolve/main/action_tokenizer/alpha_per_source.json
97 Bytes
| { | |
| "mode": "none", | |
| "note": "placeholder; per-source alpha is Phase 6", | |
| "global_scale": 1.0 | |
| } |