Zero-Shot Image Classification
Transformers
Safetensors
English
qwen2_5_vl
mmeb
multimodal
text-generation-inference
Instructions to use moca-embed/MoCa-Qwen25VL-3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use moca-embed/MoCa-Qwen25VL-3B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-image-classification", model="moca-embed/MoCa-Qwen25VL-3B") pipe( "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/hub/parrots.png", candidate_labels=["animals", "humans", "landscape"], )# Load model directly from transformers import AutoProcessor, Qwen2_5ForEmbedding processor = AutoProcessor.from_pretrained("moca-embed/MoCa-Qwen25VL-3B") model = Qwen2_5ForEmbedding.from_pretrained("moca-embed/MoCa-Qwen25VL-3B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update pipeline tag and paper link
#1
by nielsr HF Staff - opened
This PR improves the model card by:
- Changing the
pipeline_tagfromzero-shot-image-classificationtofeature-extraction, which more accurately describes the model's core function as a multimodal embedding model. This ensures better discoverability at https://huggingface.co/models?pipeline_tag=feature-extraction. - Updating the paper link to the official Hugging Face paper page: https://huggingface.co/papers/2506.23115.