huyphan168

autogen

A programming framework for agentic AI 🤖

maybe

The OS for your personal finances

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

sourcegraph

Code AI platform with Code Search & Cody

WizardLM

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

gpt-migrate

Easily migrate your codebase from one framework or language to another.

cutlass

CUDA Templates for Linear Algebra Subroutines

Pearl

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

learn2learn

A PyTorch Library for Meta-learning Research

vector-quantize-pytorch

Vector (and Scalar) Quantization, in Pytorch

datasketch

MinHash, LSH, LSH Forest, Weighted MinHash, HyperLogLog, HyperLogLog++, LSH Ensemble and HNSW

EasyEdit

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

lagent

A lightweight framework for building LLM-based agents

LLMCompiler

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

llm-reasoners

A library for advanced large language model reasoning

SeaGOAT

local-first semantic code search engine

Notion-to-Obsidian-Converter

Converts exported Notion notes to work with Obsidian.

stack-graphs

Rust implementation of stack graphs

torchopt

TorchOpt is an efficient library for differentiable optimization built upon PyTorch.

cuda_hgemm

Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

Eurus

loraplus

RepoPilot

Repo-Level Coding Assistant that Can Understand Your Whole Codebase

latentplan

Code release for Efficient Planning in a Compact Latent Action Space (ICLR2023) https://arxiv.org/abs/2208.10291.

DiffusionLLM

Code for paper "Diffusion Language Models Can Perform Many Tasks with Scaling and Instruction-Finetuning"

RepoHyper

Graph-based method for end-to-end code completion with context awareness on repository

Bridge_Gap_Diffusion

Robust-Optimization-Electric-Vehicles

Experiment with real-world data to compare the results of different algorithms in optimizing electric vehicles's scheduling.

reckoning-metakg

RECKONING is a bi-level learning algorithm that improves language models' reasoning ability by folding contextual knowledge into parametric knowledge through back-propagation.