romnoj

vector-db-benchmark

Framework for benchmarking vector search engines

colima

Container runtimes on macOS (and Linux) with minimal setup

croc

Easily and securely send things from one computer to another :crocodile: :package:

LLM-Agent-Paper-List

The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.

swift-format

Formatting technology for Swift source code

nougat

Implementation of Nougat Neural Optical Understanding for Academic Documents

glicol

Graph-oriented live coding language and music/audio DSP library written in Rust

guidance

A guidance language for controlling large language models.

KoboldAI

KoboldAI is generative AI software optimized for fictional use, but capable of much more!

text-generation-webui

A Gradio web UI for Large Language Models.

imessage-exporter

Export iMessage data + run iMessage Diagnostics

llama2.c

Inference Llama 2 in one file of pure C

tinyvector

A tiny embedding database in pure Rust.

zola

A fast static site generator in a single binary with everything built-in. https://www.getzola.org

wanda

A simple and effective LLM pruning approach.

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

bitsandbytes

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

SpQR

just

🤖 Just a command runner

flash-attention

Fast and memory-efficient exact attention

instructor-embedding

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

py-spy

Sampling profiler for Python programs

llama-cpp-python

Python bindings for llama.cpp

landmark-attention

Landmark Attention: Random-Access Infinite Context Length for Transformers

Overcooked-AI

Offline Multi-Agent Reinforcement Learning Implementations: Solving Overcooked Game with Data-Driven Method

cule

CuLE: A CUDA port of the Atari Learning Environment (ALE)

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

SAMed

The implementation of the technical report: "Customized Segment Anything Model for Medical Image Segmentation"

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.