Log inSign up
user avatar
TT Nguyen
@Machine1235
Author of GRPO-Zero library, PhD, AlphaZero in JAX, text-to-speech models, mechanistic interpretability, exploring neural nets' internal circuits...
Singapore
github.com/ntt123
Joined February 2012
726
Following
296
Followers
RepliesArticlesMedia
  • Pinned
    user avatar
    TT Nguyen
    @Machine1235
    Apr 13, 2025
    My weekend project: GRPO:Zero. An implementation of the GRPO algorithm from scratch, with zero dependencies. Say goodbye to unnecessary abstractions, every line of code is visible and everything is customizable. Runs on a single A40 GPU (48GB VRAM) for a few hours to achieve
  • user avatar
    TT Nguyen
    @Machine1235
    Jul 7
    Nice work on J-space! Fun coincidence, I explored a very similar technique called logit prisms two years ago: neuralblog.github.io/logit-prisms/ @Jack_W_Lindsey might be worth a look, and a citation would mean a lot if it fits!
  • user avatar
    TT Nguyen
    @Machine1235
    Jun 4
    ok i really like this model architecture, which somewhat proves my intuition that we don't really need a deep encoder for vision/audio modalities, the transformer backbone itself can process the image/audio tokens raw. The vision/audio encoder should be considered to play the
    user avatar
    Google Gemma
    Google for Developers
    @googlegemma
    Jun 3
    Meet Gemma 4 12B! A unified, encoder-free multimodal model designed to bring high-performance intelligence directly to your laptop, and released under an Apache 2.0 license. Bridging the gap between edge efficiency and advanced reasoning. Here is what’s new with Gemma 4 12B: 👇
    Image