NEW FUYU-8B LLM (multimodal)

New Vision Language Model AI (VLM) without a vision encoder. With reduced computational complexity, real fast and can answer questions about images?

A start-up in San Francisco presents its new FUYU 8B LLM under a non-commercial license.

Links to HuggingFace:
https://huggingface.co/adept/fuyu-8b
https://huggingface.co/adept

#ai
#aieducation
#fuyu

commercial complexity computational encoder fuyu-8b huggingface images language language model license llm multimodal questions san francisco start-up vision vlm