Sign in

Prince Canuma

@prince-canuma.bsky.social
109 followers 3 following 13 posts
PostsRepliesMedia
Prince Canuma @prince-canuma.bsky.social · 25/12/2024
QvQ-72B-Preview now on MLX 🚀🎄 TLDR 🏆SoTA open-source multimodal 🧠 Capable of step-by-step reasonin 🔥 Beats GPT-4o and Sonnet 3.5 on MathVista and MathVision You can now run inference and finetune (QLora) locally on your Mac. > pip install mlx-vlm Model cards 👇🏽 huggingface.co/collections/...
huggingface.co
QVQ-72B-Preview - a mlx-community Collection
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
020
Prince Canuma @prince-canuma.bsky.social · 06/12/2024
mlx-vlm v0.1.4 is here 🎉 New models: - @GoogleDeepMind Paligemma 2 Up next 🚧: - Refactoring Get started: > pip install -U mlx-vlm Please leave us a star and send a PR :) github.com/Blaizzy/mlx-...
021
Prince Canuma @prince-canuma.bsky.social · 26/11/2024
After some changes, @hf.co SmolVLM now does +110 tok/s on M1 Max using MLX🚀 Thanks Awni from Apple for some of the suggestions ❤️
021
Prince Canuma @prince-canuma.bsky.social · 26/11/2024
@hugg Idefics 3 and SmolVLM now on MLX 🎉🚀 You can now run inference and fine-tune locally on your Mac. pip install -U mlx-vlm I’m getting ~140 tok/s on M3 Max 96GB 🔥 Thanks to @pcuenq.hf.co for PR! Model Cards 👇🏽
162
Prince Canuma @prince-canuma.bsky.social · 24/11/2024
mlx-vlm v0.1.1 is here 🎉🔥 New models🤖: - Allen AI Molmo - Microsoft Florence 2 Changes 🚀: - Fixed Pixtral image prompt h/t Nils - 30-60% faster Qwen2-VL inference h/t Awni - Fixed Qwen2-VL OCR - Skip quant for vision encoder or layers. - New notebooks Please leave us a star and send a PR❤️
150
Prince Canuma @prince-canuma.bsky.social · 23/11/2024
The MLX King has arrived :)
020