Yoshinari Fujinuma (akkikiki)

akkikiki

Geek Repo

Company:AWS AI Labs

Location:New York, USA

Home Page:http://akkikiki.github.io

Twitter:@akkikiki

Github PK Tool:Github PK Tool

Yoshinari Fujinuma's starred repositories

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.

Language:PythonLicense:MITStargazers:165068Issues:1561Issues:2408

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.

Language:PythonLicense:Apache-2.0Stargazers:36862Issues:430Issues:1641

MiniGPT-4

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

Language:PythonLicense:BSD-3-ClauseStargazers:25181Issues:222Issues:452

StableLM

StableLM: Stability AI Language Models

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:15849Issues:201Issues:76

peft

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

Language:PythonLicense:Apache-2.0Stargazers:15184Issues:105Issues:974

web-llm

High-performance In-browser LLM Inference Engine

Language:TypeScriptLicense:Apache-2.0Stargazers:11858Issues:112Issues:266

open-llms

đź“‹ A list of open LLMs available for commercial use.

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

Language:Jupyter NotebookLicense:MITStargazers:9741Issues:84Issues:247

FlexGen

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

Language:PythonLicense:Apache-2.0Stargazers:9089Issues:109Issues:81
Language:PythonLicense:Apache-2.0Stargazers:9016Issues:121Issues:98

tokenizers

đź’Ą Fast State-of-the-Art Tokenizers optimized for Research and Production

Language:RustLicense:Apache-2.0Stargazers:8740Issues:122Issues:960

mesh-transformer-jax

Model parallel transformers in JAX and Haiku

Language:PythonLicense:Apache-2.0Stargazers:6250Issues:112Issues:205

bitsandbytes

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

Language:PythonLicense:MITStargazers:5756Issues:48Issues:968

LLaMA-Adapter

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

Language:PythonLicense:GPL-3.0Stargazers:5624Issues:78Issues:141

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

Language:PythonLicense:Apache-2.0Stargazers:2565Issues:32Issues:101

adapters

A Unified Library for Parameter-Efficient and Modular Transfer Learning

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:2478Issues:30Issues:376

pycountry

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

Language:PythonLicense:LGPL-2.1Stargazers:725Issues:13Issues:135

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.

Language:PythonLicense:Apache-2.0Stargazers:624Issues:20Issues:68
Language:PythonLicense:Apache-2.0Stargazers:575Issues:18Issues:22

examples

Fast and flexible reference benchmarks

Language:ShellLicense:Apache-2.0Stargazers:428Issues:15Issues:40

pixel

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

Language:PythonLicense:Apache-2.0Stargazers:327Issues:7Issues:16

ACL2022_KnowledgeNLP_Tutorial

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

deepform

Experimental form data extraction for journalism

Language:PythonLicense:MITStargazers:76Issues:2Issues:31

llm_family_chart

LLM family chart

License:MITStargazers:51Issues:4Issues:0

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"

Language:Jupyter NotebookLicense:MITStargazers:30Issues:4Issues:3

exploring-clmd-divergences

The code and data for the ACL paper

Language:PythonStargazers:4Issues:4Issues:0