News for hackers. Stuff that matters.

A comment on Fastvlm: Efficient vision encoding for vision language models.

Re:Fastvlm: Efficient vision encoding for vision language mo... by d3k on Tuesday May 13, 2025 @05:51AM (#43971261)
Very nice! I wish they were more keen to contribute to AI/ML community an publish weights and model definition on HuggingFace. Funny enough I have just seen today a similar demo that is using a freely available VLM: https://github.com/ngxson/smolvlm-realtime-webcam
[ Parent | on HN ]
Re:Fastvlm: Efficient vision encoding for vision language mo... by tough on Tuesday May 13, 2025 @07:34AM (#43971752)
SmolVLM is from huggingface team

cool to see people doing stuff with smaller models

https://huggingface.co/blog/smolvlm

https://arxiv.org/abs/2504.05299

[ Parent | on HN ]