akkikiki

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

llama.cpp

LLM inference in C/C++

Open-Assistant

OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

StableLM

StableLM: Stability AI Language Models

peft

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

web-llm

High-performance In-browser LLM Inference Engine

open-llms

📋 A list of open LLMs available for commercial use.

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

FlexGen

Running large language models on a single GPU for throughput-oriented scenarios.

OpenChatKit

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

mesh-transformer-jax

Model parallel transformers in JAX and Haiku

bitsandbytes

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

LLaMA-Adapter

[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

xTuring

Build, customize and control you own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

adapters

A Unified Library for Parameter-Efficient and Modular Transfer Learning

pycountry

A Python library to access ISO country, subdivision, language, currency and script definitions and their translations.

llmtools

Finetuning Large Language Models on One Consumer GPU in Under 4 Bits

xtreme

XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.

pix2struct

examples

Fast and flexible reference benchmarks

pixel

Research code for pixel-based encoders of language (PIXEL)

ACL2022_KnowledgeNLP_Tutorial

Materials for ACL-2022 tutorial: Knowledge-Augmented Methods for Natural Language Processing

UDOP

xquad

deepform

Experimental form data extraction for journalism

llm_family_chart

LLM family chart

udapter

UDapter is a multilingual dependency parser that uses "contextual" adapters together with language-typology features for language-specific adaptation. This repository includes the code for "UDapter: Language Adaptation for Truly Universal Dependency Parsing"

exploring-clmd-divergences

The code and data for the ACL paper