Image-to-Text
Transformers
Safetensors
English
cambrian_qwen
text-generation
multimodal
video-understanding
spatial-reasoning
vision-language
Instructions to use nyu-visionx/Cambrian-S-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nyu-visionx/Cambrian-S-3B with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-text" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("image-to-text", model="nyu-visionx/Cambrian-S-3B")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("nyu-visionx/Cambrian-S-3B", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K