Pedro Cuenca
pcuenq.hf.co
Pedro Cuenca
@pcuenq.hf.co
ML Engineer at Hugging Face
Love it! Are you planning to transfer the sense of humor as well? 😀
February 21, 2025 at 10:06 PM
I used to disable Sleep in the settings, but allowing the display to go off; now it looks like that combination is no longer possible :(
January 9, 2025 at 11:00 AM
More info:
⛰️ Andi's post bsky.app/profile/andi...
📖 Blog post huggingface.co/blog/smolvlm
💃🏻 Models huggingface.co/collections/...
🎮 HF Demo huggingface.co/spaces/Huggi...
🔨 mlx-vlm PR [WIP] github.com/Blaizzy/mlx-...
Let's go! We are releasing SmolVLM, a smol 2B VLM built for on-device inference that outperforms all models at similar GPU RAM usage and tokens throughputs.

SmolVLM can be fine-tuned on a Google collab and be run on a laptop! Or process millions of documents with a consumer GPU!
November 26, 2024 at 4:37 PM