If you find my projects useful, please star and follow! Everything here comes from my free time, and is released under permissive licenses (e.g. MIT). Send me an email or open an issue if you'd like to discuss a past/current/future project.
- Huntsville, AL
- in/frank-odom
- https://fkodom.substack.com
Highlights
- Pro
Pinned Loading
-
fft-conv-pytorch
fft-conv-pytorch PublicImplementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.
-
yet-another-retnet
yet-another-retnet PublicA 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)
-
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)
-
transformer-from-scratch
transformer-from-scratch PublicCode implementation from my blog post: https://fkodom.substack.com/p/transformers-from-scratch-in-pytorch
-
clip-text-decoder
clip-text-decoder PublicGenerate text captions for images from their embeddings.
-
soft-mixture-of-experts
soft-mixture-of-experts PublicPyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)
If the problem persists, check the GitHub status page or contact support.