rayruiyang

/

VST-7B-SFT

like 0

This PR enhances the model card by adding key metadata and improving its clarity and discoverability:

• pipeline_tag: image-text-to-text: This tag accurately reflects the model's functionality of processing visual (image/video) and text inputs to generate text. It will help users find this model when searching for multimodal models.
• library_name: transformers: The inclusion of transformers as the library_name ensures that users are provided with an automated, functional code snippet on the model page, facilitating easier adoption. Evidence for compatibility is found in config.json, tokenizer_config.json, and the provided code snippet.
• Hugging Face Paper Link: Added a direct link to the Hugging Face paper page, complementing the existing arXiv link and improving the discoverability of the research on the platform.
• Improved Title: The model card title has been updated to # VST-7B-SFT: Visual Spatial Tuning for better clarity.
• "Sample Usage" Section: The "Quickstart" section has been renamed to "Sample Usage" and includes a clearer introduction for installing dependencies. The provided code snippet has been retained as it correctly targets VST-7B-SFT.

These updates will make the model more accessible and easier to use for the community.