Any-to-Any
Transformers
English
Chinese
qwen2
text-generation
medical
vision-language
multimodal
unified-model
medical-vqa
text-to-image
image-to-text
medical-understanding
report-generation
interleaved-multimodal
modality-transfer
custom_code
Instructions to use General-Medical-AI/UniMedVL with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use General-Medical-AI/UniMedVL with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForMultimodalLM tokenizer = AutoTokenizer.from_pretrained("General-Medical-AI/UniMedVL", trust_remote_code=True) model = AutoModelForMultimodalLM.from_pretrained("General-Medical-AI/UniMedVL", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
Enhance model card with detailed information and `library_name: transformers`
#1
by nielsr HF Staff - opened
This PR significantly enhances the model card for UniMedVL by incorporating comprehensive details from the official GitHub repository.
Key improvements include:
- Addition of
library_name: transformersto the metadata, enabling the automated "how to use" widget on the Hugging Face Hub due to the model's compatibility with the Transformers library (as evidenced byllm_config.json). - Expansion of the content to include an in-depth introduction, methodology, open-source plan, qualitative and quantitative results, and detailed "Getting Started" instructions, providing users with a richer understanding of the model's capabilities and usage.
- Integration of the paper's abstract to offer a concise summary.
- Updated and consolidated author information, linking to Hugging Face profiles where available.
These changes aim to make the UniMedVL model card more informative and user-friendly.
junzhin changed pull request status to merged
Thank you so much !!