Robotics
Transformers
Safetensors
paligemma
image-text-to-text
vision-language-action
chain-of-thought
embodied-ai
text-generation-inference
Instructions to use yinchenghust/deepthinkvla_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use yinchenghust/deepthinkvla_base with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("yinchenghust/deepthinkvla_base") model = AutoModelForMultimodalLM.from_pretrained("yinchenghust/deepthinkvla_base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "<image>": 257152, | |
| "<think>": 257153, | |
| "</think>": 257154, | |
| "<action>": 257155, | |
| "</action>": 257156 | |
| } | |