mdeff

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

llama3

The official Meta Llama 3 GitHub site

wasmer

🚀 The leading Wasm Runtime supporting WASIX, WASI and Emscripten

mlx

MLX: An array framework for Apple silicon

open-gpu-kernel-modules

NVIDIA Linux open GPU kernel module source

lm-evaluation-harness

A framework for few-shot evaluation of language models.

bitsandbytes

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

CLRS

📚 Solutions to Introduction to Algorithms Third Edition

RedPajama-Data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

torchtune

A Native-PyTorch Library for LLM Fine-tuning

matmulfreellm

Implementation for MatMul-free LM.

wasmer-python

🐍🕸 WebAssembly runtime for Python

til

Today I Learned

ao

Custom data types and layouts for training and inference

worldmodels.github.io

World Models

RestrictedPython

A restricted execution environment for Python to run untrusted code.

wasmtime-py

Python WebAssembly runtime powered by Wasmtime

codejail

Secure code execution

transformer-quantization

LiveBench

LiveBench: A Challenging, Contamination-Free LLM Benchmark

geometric-algebra-transformer

FP8-quantization

Skip-Conv

arc-notes

My writings about ARC (Abstraction and Reasoning Corpus)

mindscript

A programming language for formal/informal computation.

iglu-datasets

codeit

paper-snn-neurips2020tda

LaTeX source code of the paper and poster of the paper Simplicial Neural Networks

DEHNN

Github repository of the AIStats 2024 paper: DE-HNN: An effective neural model for Circuit Netlist representation