Skip to content
View fkodom's full-sized avatar

Highlights

  • Pro
Block or Report

Block or report fkodom

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
fkodom/README.md

trophies

streak-stats

If you find my projects useful, please consider becoming a sponsor. Everything here comes from my free time, and is released under permissive licenses (e.g. MIT). Your contribution helps fund open-source AI.

buymeacoffee

Pinned

  1. fft-conv-pytorch fft-conv-pytorch Public

    Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.

    Python 440 53

  2. yet-another-retnet yet-another-retnet Public

    A simple but robust PyTorch implementation of RetNet from "Retentive Network: A Successor to Transformer for Large Language Models" (https://arxiv.org/pdf/2307.08621.pdf)

    Python 94 15

  3. transformer-from-scratch transformer-from-scratch Public

    Code implementation from my blog post: https://fkodom.substack.com/p/transformers-from-scratch-in-pytorch

    Python 89 19

  4. clip-text-decoder clip-text-decoder Public

    Generate text captions for images from their embeddings.

    Python 87 3

  5. grouped-query-attention-pytorch grouped-query-attention-pytorch Public

    (Unofficial) PyTorch implementation of grouped-query attention (GQA) from "GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints" (https://arxiv.org/pdf/2305.13245.pdf)

    Python 78 4

  6. soft-mixture-of-experts soft-mixture-of-experts Public

    PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)

    Python 57 3