Instructions to use jcwang0602/MLLMSeg_InternVL2_5_4B_RES with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jcwang0602/MLLMSeg_InternVL2_5_4B_RES with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-segmentation", model="jcwang0602/MLLMSeg_InternVL2_5_4B_RES", trust_remote_code=True)# Load model directly from transformers import MLLMSeg model = MLLMSeg.from_pretrained("jcwang0602/MLLMSeg_InternVL2_5_4B_RES", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add comprehensive model card for MLLMSeg_InternVL2_5_4B_RES
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card for MLLMSeg_InternVL2_5_4B_RES by adding:
- The
pipeline_tag: image-segmentationto correctly categorize the model on the Hugging Face Hub, making it easily discoverable at https://huggingface.co/models?pipeline_tag=image-segmentation. - The
library_name: transformersto indicate compatibility with the Hugging Facetransformerslibrary, enabling the "How to use" widget. - Direct links to the paper and the official GitHub repository for easy access to more information and code.
- A practical Python usage example for quick inference, directly from the official repository.
- Performance metrics and visualization examples to showcase the model's capabilities.
jcwang0602 changed pull request status to merged