pepsighan

gpt-prompt-engineer

jan

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. Multiple engine support (llama.cpp, TensorRT-LLM)

loguru

Python logging made (stupidly) simple

burn

Burn is a new comprehensive dynamic Deep Learning Framework built using Rust with extreme flexibility, compute efficiency and portability as its primary goals.

ladybird

Truly independent web browser

dominate

Dominate is a Python library for creating and manipulating HTML documents using an elegant DOM API. It allows you to write HTML pages in pure Python very concisely, which eliminate the need to learn another template language, and to take advantage of the more powerful features of Python.

pebble

Multi threading and processing eye-candy.

sympytorch

Turning SymPy expressions into PyTorch modules.

mlx

MLX: An array framework for Apple silicon

lineclipping-python-fortran

Line clipping in clean, simple, modern Fortran and Python

python-dotenv

Reads key-value pairs from a .env file and can set them as environment variables. It helps in developing applications following the 12-factor principles.

next-auth

Authentication for the Web.

make-real

Draw a ui and make it real

llm-vscode

LLM powered development for VSCode

llm.c

LLM training in simple, raw C/CUDA

pathfinding

Pathfinding library for rust

fastest-levenshtein

The fastest implementation of Levenshtein distance in JS/TS.

mypy_boto3_builder

Type annotations builder for boto3 compatible with VSCode, PyCharm, Emacs, Sublime Text, pyright and mypy.

summarize-from-feedback

Code for "Learning to summarize from human feedback"

unsloth

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

accelerate

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

optimum-quanto

A pytorch quantization backend for optimum

mergekit

Tools for merging pretrained large language models.

LoRA

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

bpemb

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

machine-learning-articles

🧠💬 Articles I wrote about machine learning, archived from MachineCurve.com.

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API