Live data from Hacker News

Viewing profile — bornaahz

bornaahz

HN member
Joined
Mon, Apr 29, 2024, 7:34 PM UTC
HN karma
11
Public activity
12 items

About bornaahz

Machine learning engineer

Recent public activity

  1. story
  2. story
  3. story
  4. story
  5. comment
    Comment #41797866

    Thanks a ton! It means a lot.

  6. comment
    Comment #41787055

    Hello everyone, I am the author of this project. If anyone has any questions concerning trap, I'd be more than happy to address them.

  7. story
  8. story
  9. story
    Show HN: Flaim – pre-trained vision backbones for Flax

    flaim is a library of state-of-the-art pre-trained vision models, plus common deep learning modules in computer vision, for JAX/Flax. It exposes a host of diverse image models thro…

  10. story
    Show HN: OpenCLIP Jax – Implementation of OpenAI's Clip in Jax/Flax

    open_clip_jax is an open source JAX/Flax implementation of OpenAI's CLIP, including image and text towers, pre-trained parameters, training utilities that can scale to TPU Pods, an…

  11. story
    Show HN: Minbpe-hs – byte-level byte pair encoding (BPE) in Haskell

    minbpe-hs is a port of Andrej Karpathy's concise byte-level byte pair encoding (BPE) implementation, minbpe, to Haskell. During training, BPE compresses a sequence by repeatedly fi…

  12. story
    Show HN: Attorch – PyTorch's nn module written in Python using OpenAI's Triton

    attorch is a subset of PyTorch's nn module, written purely in Python using OpenAI's Triton. Its goal is to be an easily hackable, self-contained, and readable collection of neural …