Fine-tuning Llama 3.1, researchers at MBZUAI built BiMediX2, an Arabic-English VLM for medical use cases that excels in both text and visual tasks — including interpreting medical images from X-Rays, CT scans, MRIs and more. The models and datasets will be available publicly on Hugging Face. https://www.threads.net/@aiatmeta/post/DDsBgdjSZOu?xmt=AQGzc7UBV0Z5GiAXQKSFZyLQ87pn-t223H0kUIU7zzX0vw