Frank Odom (@fkodom)
github

fkodom

Twitter logo Share LinkedIn logo Share Facebook logo Share
  • Stars
    star
    969
  • Global Rank 30,843 (Top 2 %)
  • Followers 266
  • Following 27
  • Registered over 5 years ago
  • Most used languages
    Python
         95.7 %
    Dockerfile
         4.3 %
  • Location πŸ‡ΊπŸ‡Έ United States
  • Country Total Rank 12,946
  • Country Ranking
    Python
         1,490
    Dockerfile
         5,149

Top repositories

1

fft-conv-pytorch

Implementation of 1D, 2D, and 3D FFT convolutions in PyTorch. Much faster than direct convolutions for large kernel sizes.
Python
433
star
2

yet-another-retnet

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
91
star
3

transformer-from-scratch

Code implementation from my blog post: https://fkodom.substack.com/p/transformers-from-scratch-in-pytorch
Python
88
star
4

clip-text-decoder

Generate text captions for images from their embeddings.
Python
85
star
5

grouped-query-attention-pytorch

(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
71
star
6

soft-mixture-of-experts

PyTorch implementation of Soft MoE by Google Brain in "From Sparse to Soft Mixtures of Experts" (https://arxiv.org/pdf/2308.00951.pdf)
Python
53
star
7

dilated-attention-pytorch

(Unofficial) Implementation of dilated attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens" (https://arxiv.org/abs/2307.02486)
Python
44
star
8

wnet-unsupervised-image-segmentation

Python
25
star
9

semantle

Fastest 'Semantle' solver this side of the Mississippi.
Python
14
star
10

python-repo-template

Template repo for Python projects, especially those focusing on machine learning and/or deep learning.
Python
10
star
11

document-rag

RAG application to answer questions about PDF documents using LLMs.
Python
9
star
12

byol

PyTorch implementation of BYOL: a fantastically simple method for self-supervised image representation learning with SOTA performance.
Python
9
star
13

lora-pytorch

Simple but robust implementation of LoRA for PyTorch. Compatible with NLP, CV, and other model types. Strongly typed and tested.
Python
7
star
14

blip-inference

Pretrained BLIP with a similar API to CLIP.
Python
5
star
15

octconv-pytorch

Python
5
star
16

metis

Minimalist library for training RL agents in PyTorch. Implements many common training algorithms, with a focus on actor-critic methods. Includes SAC, TD3, PPO, A2C, VPG.
Python
5
star
17

simple-cocotools

A simple, modern alternative to 'pycocotools'.
Python
3
star
18

unipipe

Build batch pipelines in Python that run anywhere.
Python
3
star
19

ncsn

Personal repo recreating Noise Contrastive Score Networks (https://arxiv.org/abs/1907.05600v2) for learning purposes.
Python
2
star
20

wordle

Fastest Wordle solver in the West.
Python
2
star
21

docker-images

Repository for automatically building base Docker images with Github Actions.
Dockerfile
1
star
22

flaxseed

(Personal) Training library build on top of Flax, making it easier to train deep learning models with Jax. Because Flax is great, but doesn't take things far enough.
Python
1
star
23

ddpg-her-pytorch

Implementation of the Hindsight Experience Replay (HER) algorithm using PyTorch. Utilizes Deep Deterministic Policy Gradients for off-policy optimization of RL agents in continuous action spaces.
Python
1
star