Light's picture

8

Light

pylotlight

·

AI & ML interests

None yet

Recent Activity

new activity about 16 hours ago

mistralai/Voxtral-4B-TTS-2603:MLX Optimisation for running locally?

reacted to mitkox's post with 👀 5 months ago

I see all Chinese labs are turning TL;DR into TL;DRGB Problem: 1M text tokens == 1 M opportunities for your GPU to file worker-comp Solution: don’t feed the model War & Peace—feed it the movie poster. This is Glyph, Zai’s new visual-text compression voodoo: • 10 k words → 3 PNGs ≈ 3 k visual tokens • Compression ratio: 4.3× • Throughput: 40-60 tok/s i.e. your context window now finishes before my coffee does So I did the only reasonable thing: asked GLM-4.6 to port Glyph for Qwen3-VL-8B-Thinking. Translation: I made one model compress a novel into a comic strip, then made another model read the comic strip and still ace QA. It’s basically passing notes in class, except the note is a 1920×1080 meme and the teacher is a transformer. We've gone from "Attention is All You Need" to "Attention is Too Expensive, Just Use Your Eyes." Remember kids: in 2025 literacy is optional, but JPEG is forever.

new activity 6 months ago

openbmb/VoxCPM-Demo:I believe the model works best when processed sentence by sentence

View all activity

Organizations

None yet

models 0

None public yet

datasets 0

None public yet