medcap-pmcoa
The vision encoder is fine-tuned from BiomedCLIP using Meta-Llama-3-8B-Instruct. For more information, please refer to medcap and README_FINETUNE.md.
The model is still in training, and the current version is preliminary.
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.