Jeremy Howard

Cofounder of fast.ai

Starred Projects (219)

Awesome-Model-Merging-Methods-Theories-Applications by EnnengYang

Survey of model merging methods, theories, applications for LLMs & MLLMs

Created 2 years ago

Updated 5 days ago

slime by THUDM

LLM post-training framework for RL scaling

geohot:

ekzhu:

ekzhang:

didierrlopes:

Created 1 year ago

Updated 7 hours ago

Fun-ASR by QwenAudio

Advanced speech recognition toolkit for global audio

Created 9 months ago

Updated 1 month ago

cli by googleworkspace

Unified CLI for Google Workspace with AI agent integration

khou22:

swyxio:

developit:

mjackson:

Created 7 months ago

Updated 3 days ago

KittenTTS by KittenML

Realistic text-to-speech model under 25MB

jrk:

hugs:

bryanhelmig:

omarsar:

Created 1 year ago

Updated 3 days ago

mini-sglang by sgl-project

Lightweight LLM inference framework with advanced optimizations

bryanhelmig:

merrymercy:

Ying1123:

Created 1 year ago

Updated 4 months ago

Claudeception by blader

AI coding agents that learn and retain knowledge

dguido:

taranjeet:

Created 8 months ago

Updated 7 months ago

claude-office-skills by tfriedel

Office document automation and editing for command-line AI

Created 1 year ago

Updated 6 months ago

tokenmonster by alasdairforsythe

Subword tokenizer and vocabulary trainer for multiple languages

chiphuyen:

stas00:

lucidrains:

Created 3 years ago

Updated 3 months ago

simple-llm by naklecha

Minimal, extensible LLM inference engine

Created 9 months ago

Updated 9 months ago

chrome-devtools-mcp by benjaminr

AI-powered debugging bridge for web applications

Created 1 year ago

Updated 1 year ago

dots.ocr by studio-dots-ai

Multilingual document layout parsing with a single vision-language model

hammer:

transitive-bullshit:

amin3141:

Created 1 year ago

Updated 6 months ago

claude-code-docs by ericbuess

Local Claude documentation access

hiyouga:

Created 1 year ago

Updated 1 day ago

jupyter-mcp-server by datalayer

MCP server for Jupyter notebooks

khou22:

Created 1 year ago

Updated 5 days ago

Fabric by danielmiessler

AI augmentation framework for human flourishing

joewalnes:

spelsbergsam:

jrk:

jn2clark:

Created 2 years ago

Updated 3 days ago

streamdown by day50-dev

Streaming Markdown parser for TUIs

willingc:

jrk:

simonw:

Created 1 year ago

Updated 3 weeks ago

repeng by vgel

Python library for representation engineering control vectors

willccbb:

winglian:

tgaddair:

Created 2 years ago

Updated 1 year ago

git-mcp by idosal

MCP server for connecting AI tools to GitHub repos

mxcl:

hsbt:

transitive-bullshit:

Created 1 year ago

Updated 5 months ago

Qwen-Agent by QwenLM

Agent framework for LLM application development

hammer:

ekzhu:

ogabrielluiz:

thomwolf:

Created 3 years ago

Updated 7 months ago

Moonlight by MoonshotAI

MoE model and optimizer tech report

lucidrains:

zhyncs:

Created 1 year ago

Updated 1 year ago

s1 by simplescaling

Test-time scaling recipe for strong reasoning performance

lewtun:

shizhediao:

taranjeet:

chiphuyen:

Created 1 year ago

Updated 1 year ago

ModernBERT by AnswerDotAI

Research repo for modernizing BERT via architecture and scaling

chiphuyen:

bryanhelmig:

hammer:

ogabrielluiz:

Created 2 years ago

Updated 7 months ago

markitdown by microsoft

Python tool for converting files to Markdown for LLM text analysis

mojombo:

chiphuyen:

omarsar:

handotdev:

Created 1 year ago

Updated 6 days ago

logits-processor-zoo by NVIDIA

Logits processor collection for customizing LLM behavior

Created 1 year ago

Updated 3 weeks ago

skyvern by Skyvern-AI

CLI tool for browser automation using LLMs and computer vision

apsdehal:

ebursztein:

dguido:

jordn:

Created 2 years ago

Updated 1 day ago

claude-artifact-runner by claudio-silva

React template for Claude Artifact conversion to web apps

transitive-bullshit:

jxnl:

simonw:

Created 2 years ago

Updated 8 months ago

moonshine by moonshine-ai

Speech-to-text models optimized for fast, accurate ASR on edge devices

karpathy:

transitive-bullshit:

hammer:

Created 2 years ago

Updated 1 week ago

moshi by kyutai-labs

Speech-text foundation model for real-time dialogue

hammer:

LaurentMazare:

thomwolf:

osanseviero:

Created 2 years ago

Updated 1 month ago

modded-nanogpt by KellerJordan

Language model training speedrun on 8x H100 GPUs

geohot:

karpathy:

jn2clark:

lewtun:

Created 2 years ago

Updated 1 week ago

entropix by xjdr-alt

Research project for entropy-based context-aware sampling & parallel CoT decoding

geohot:

vincentweisser:

snowzurfer:

evhub:

Created 2 years ago

Updated 1 year ago

whisper-diarization by MahmoudAshraf97

ASR pipeline for speaker diarization

tjbck:

ogabrielluiz:

transitive-bullshit:

Created 3 years ago

Updated 1 month ago

argmax-oss-swift by argmaxinc

Speech recognition framework for Apple Silicon

joewalnes:

osanseviero:

transitive-bullshit:

cbh123:

Created 2 years ago

Updated 21 hours ago

whisper_streaming by ufal

Real-time streaming for long speech-to-text transcription/translation

amin3141:

Created 3 years ago

Updated 11 months ago

pyreft by stanfordnlp

Python library for representation finetuning (ReFT) of language models

hammer:

hiyouga:

winglian:

Created 2 years ago

Updated 7 months ago

LLaMA-Omni by ictnlp

Speech-language model for low-latency, high-quality speech interaction

alexchen4ai:

omarsar:

Created 2 years ago

Updated 1 year ago

whisper-writer by savbell

Dictation app using OpenAI's Whisper model for real-time transcription

Created 3 years ago

Updated 2 years ago

optillm by algorithmicsuperintelligence

Optimizing inference proxy for LLMs

chiphuyen:

rasbt:

casper-hansen:

marcklingen:

Created 2 years ago

Updated 1 week ago

MiniCPM-V by OpenBMB

MLLM for vision, speech, and multimodal live streaming on your phone

hammer:

luiscape:

chiphuyen:

ebursztein:

Created 2 years ago

Updated 1 month ago

AidanBench by aidanmclaughlin

LLM benchmark for evaluating creativity and open-ended question answering

Created 2 years ago

Updated 1 year ago

torchtitan by pytorch

PyTorch platform for generative AI model training research

karpathy:

WoosukKwon:

pgarbacki:

lewtun:

Created 2 years ago

Updated 9 hours ago

whisper-medusa by aiola-lab

ASR optimization via multi-head decoding

Created 2 years ago

Updated 3 months ago

Open-Reasoning-Tasks by NousResearch

Reasoning tasks collection for LLMs

zjasper666:

winglian:

JohannesHa:

philschmid:

Created 2 years ago

Updated 2 years ago

llm-datasets by mlabonne

Curated datasets/tools for LLM post-training

jn2clark:

soldni:

shyamal-anadkat:

philschmid:

Created 2 years ago

Updated 5 months ago

insanely-fast-whisper-cli by ochen1

CLI tool for optimized, fast Whisper-based ASR

Created 3 years ago

Updated 2 years ago

clarity-upscaler by philz1337x

AI image upscaler & enhancer, alternative to Magnific

chiphuyen:

Created 2 years ago

Updated 1 year ago

minRF by cloneofsimo

Minimal implementation of rectified flow transformers, based on SD3

andreasjansson:

Created 2 years ago

Updated 2 years ago

on-device-transcription by Hugo-Dz

Minimal app for on-device speech-to-text conversion

Created 2 years ago

Updated 2 years ago

Prompt-Engineering-Toolkit by teknium1

Web app for LLM prompt experimentation and optimization

vincentweisser:

teknium1:

Created 2 years ago

Updated 2 years ago

sonar by dphnAI

LLM inference engine for serving HuggingFace models at scale

luiscape:

shimmyshimmer:

vincentweisser:

teknium1:

Created 3 years ago

Updated 4 weeks ago

writer-framework by writer

Open-source framework for AI application development

wassemgtk:

Created 4 years ago

Updated 1 week ago

unilm by microsoft

Foundation models for language, vision, speech, and multimodal tasks

AlexCheema:

chiphuyen:

osanseviero:

parano:

Created 7 years ago

Updated 2 weeks ago

MoRA by kongds

Parameter-efficient fine-tuning via high-rank updating (MoRA)

winglian:

Created 2 years ago

Updated 2 years ago

flash-linear-attention by fla-org

Efficient Torch/Triton implementations for linear attention models

didierrlopes:

hiyouga:

xiezhq-hermann:

zhyncs:

Created 2 years ago

Updated 12 hours ago

Scrapegraph-ai by ScrapeGraphAI

Python library for AI-powered web scraping

thinkall:

marcklingen:

rodrigosnader:

pirroh:

Created 2 years ago

Updated 4 days ago

cohere-toolkit by cohere-ai

RAG toolkit for LLM application development and deployment

chiphuyen:

willccbb:

pgarbacki:

transitive-bullshit:

Created 2 years ago

Updated 6 months ago

code-interpreter by e2b-dev

SDK for running AI-generated code in secure cloud sandboxes

hiyouga:

hammer:

chiphuyen:

yiranwu0:

Created 2 years ago

Updated 1 day ago

claude-cookbooks by anthropics

Code & guides for building with Claude

didierrlopes:

parano:

osanseviero:

transitive-bullshit:

Created 3 years ago

Updated 1 week ago

AgentRun by tjmlabs

Python library for safely running AI-generated code

matamalaortiz:

Created 2 years ago

Updated 3 months ago

llm.mojo by dorjeduck

Mojo port of Karpathy's llm.c for GPT-2 training

parano:

iamtimdavis:

hammer:

Created 2 years ago

Updated 6 days ago

llama3 by meta-llama

*Deprecated* minimal example for loading and running Llama 3 models

tobi:

mckaywrigley:

osanseviero:

simonw:

Created 2 years ago

Updated 1 year ago

faster-whisper by SYSTRAN

Faster Whisper reimplementation using CTranslate2

dguido:

luiscape:

tjbck:

chiphuyen:

Created 3 years ago

Updated 11 hours ago

attorch by BobMcDear

PyTorch nn module subset, implemented in Python using Triton

karpathy:

Edward-Sun:

sualehasif:

srush:

Created 3 years ago

Updated 1 month ago

QuaRot by spcl

Code for a NeurIPS 2024 research paper on LLM quantization

zhyncs:

Created 2 years ago

Updated 1 year ago

open_lm by mlfoundations

Language model research repo for medium-sized models (up to 7B params)

shizhediao:

alexchen4ai:

vincentweisser:

hammer:

Created 3 years ago

Updated 1 year ago

distilabel by argilla-io

Framework for synthetic data and AI feedback pipelines

lvwerra:

jn2clark:

hiyouga:

pgarbacki:

Created 3 years ago

Updated 3 days ago

optimum-quanto by huggingface

PyTorch quantization backend for Hugging Face models

codekansas:

osanseviero:

thomwolf:

mfuntowicz:

Created 3 years ago

Updated 1 week ago

LLM-Workshop by pacman100

Workshop for LLM upskilling

Created 3 years ago

Updated 2 years ago

nanobind by wjakob

Tiny and efficient C++/Python bindings library

luiscape:

simonw:

awni:

jrk:

Created 4 years ago

Updated 1 week ago

LaVague by lavague-ai

Web agent framework for automating web processes

rodrigosnader:

winglian:

omarsar:

bryanhelmig:

Created 2 years ago

Updated 1 year ago

GradCache by luyug

Technique for contrastive learning beyond GPU memory limits

rwightman:

Created 5 years ago

Updated 2 years ago

maxtext by AI-Hypercomputer

Jax LLM for high-performance, scalable training/inference on TPUs/GPUs

ebursztein:

sebastiandero:

Edward-Sun:

transitive-bullshit:

Created 3 years ago

Updated 11 hours ago

neural-cherche by raphaelsty

Library for neural search model fine-tuning and efficient inference

jn2clark:

Created 3 years ago

Updated 1 year ago

ao by pytorch

PyTorch library for quantization and sparsity in training/inference

danielhanchen:

shimmyshimmer:

parano:

willccbb:

Created 2 years ago

Updated 10 hours ago

marker by datalab-to

CLI tool for converting PDFs and other documents to Markdown, JSON, and HTML

luiscape:

bfirsh:

joewalnes:

snowzurfer:

Created 2 years ago

Updated 1 week ago

GPTFast by MDK8888

HF Transformers accelerator for faster inference

chiphuyen:

mlabonne:

Created 2 years ago

Updated 2 years ago

gemma.cpp by google

C++ inference engine for Google's Gemma models

karpathy:

tjbck:

osanseviero:

chiphuyen:

Created 2 years ago

Updated 1 day ago

gpt-pilot by Pythagora-io

AI-driven app development tool

handotdev:

kelvich:

shawnlewis:

chiphuyen:

Created 3 years ago

Updated 3 months ago

Bunny by BAAI-DCAI

Multimodal models for vision-language tasks

hammer:

osanseviero:

Created 2 years ago

Updated 1 year ago

cutlass by NVIDIA

CUDA C++ and Python DSLs for high-performance linear algebra

luiscape:

pgarbacki:

pankajroark:

tridao:

Created 8 years ago

Updated 2 weeks ago

skypilot by skypilot-org

Framework for cloud AI/batch jobs, unifying execution across diverse infrastructure

karpathy:

tobi:

ekzhu:

amin3141:

Created 5 years ago

Updated 18 hours ago

bagel by jondurbin

Fine-tuning pipeline for language models, "with everything."

osanseviero:

mlabonne:

casper-hansen:

Created 2 years ago

Updated 2 years ago

xmc.dspy by KarelDO

In-context learning for extreme multi-label classification

okhat:

hammer:

Created 2 years ago

Updated 2 years ago

RAGatouille by AnswerDotAI

SDK for late-interaction retrieval (ColBERT) in RAG pipelines

ankane:

xiaofan-luan:

JustinLin610:

omarsar:

Created 2 years ago

Updated 1 year ago

nlm-ingestor by nlmatics

Server for LLM ingestion via API, enabling custom RAG parsing

timsuchanek:

Created 2 years ago

Updated 1 year ago

tensordict by pytorch

PyTorch tensor container for efficient ML data handling

srush:

rwightman:

soumith:

hammer:

Created 4 years ago

Updated 8 hours ago

plock by jasonjmcghee

CLI tool for streaming LLM output or script results directly into any text field

cbh123:

jmorganca:

Created 2 years ago

Updated 2 years ago

llm-course by mlabonne

LLM course with roadmaps and notebooks

mlabonne:

shizhediao:

shimmyshimmer:

willccbb:

Created 3 years ago

Updated 8 months ago

self-rewarding-lm-pytorch by lucidrains

Training framework for self-rewarding language models

vincentweisser:

chiphuyen:

pgarbacki:

swyxio:

Created 2 years ago

Updated 2 years ago

nanotron by huggingface

Minimalistic library for large language model pretraining

clmnt:

shizhediao:

vincentweisser:

luiscape:

Created 3 years ago

Updated 2 days ago

marlin by IST-DASLab

FP16xINT4 kernel for fast LLM inference

parano:

zhuohan123:

Created 2 years ago

Updated 2 years ago

functionary by MeetKai

Chat language model for tool use and result interpretation

ogabrielluiz:

parano:

hiyouga:

winglian:

Created 3 years ago

Updated 3 months ago

priompt by anysphere

JSX-based prompting library for context window management

truell20:

kentcdodds:

compuives:

willccbb:

Created 3 years ago

Updated 1 year ago

surya by datalab-to

Document intelligence toolkit for OCR, layout, and table recognition

amin3141:

luiscape:

gakonst:

dguido:

Created 2 years ago

Updated 4 weeks ago

funcchain by shroominic

SDK for building cognitive systems with Python

bryanhelmig:

AntonOsika:

Created 3 years ago

Updated 1 year ago

unsloth by unslothai

Finetuning tool for LLMs, targeting speed and memory efficiency

tobi:

karpathy:

alexchen4ai:

danielhanchen:

Created 2 years ago

Updated 7 hours ago

maestro by roboflow

CLI/SDK for fine-tuning multimodal models

chiphuyen:

gakonst:

osanseviero:

jwyang:

Created 2 years ago

Updated 4 days ago

GPTQ-triton by fpgaminer

Triton kernel for GPTQ inference, improving context scaling

srush:

osanseviero:

Created 3 years ago

Updated 3 years ago

prompt-lookup-decoding by apoorvumang

Decoding method for faster LLM generation

zhyncs:

stas00:

casper-hansen:

ggerganov:

Created 2 years ago

Updated 2 years ago

tldraw by tldraw

Infinite canvas SDK for building interactive web applications

ebursztein:

gakonst:

stammy:

jpamorgan:

Created 5 years ago

Updated 20 hours ago

simplified_transformers by bobby-he

Research paper implementation for simplifying transformer blocks

Created 2 years ago

Updated 1 year ago

PiPPy by pytorch

PyTorch tool for pipeline parallelism

yang-song:

JohannesHa:

stas00:

Edward-Sun:

Created 4 years ago

Updated 2 years ago

SwissArmyTransformer by THUDM

Transformer library for flexible model development

stas00:

Created 5 years ago

Updated 1 year ago

marimo by marimo-team

AI-native reactive notebooks for reproducible Python development

tobi:

bcherny:

didierrlopes:

ekzhang:

Created 3 years ago

Updated 17 hours ago

code-eval by abacaj

Evaluation harness for LLMs using the HumanEval benchmark

Created 3 years ago

Updated 3 years ago

LlamaFactory by hiyouga

Unified fine-tuning tool for 100+ LLMs & VLMs (ACL 2024)

hiyouga:

patrickvonplaten:

alexchen4ai:

teetone:

Created 3 years ago

Updated 1 week ago

multimodal by facebookresearch

PyTorch library for multimodal multi-task model training

hammer:

winglian:

chiphuyen:

vincentweisser:

Created 4 years ago

Updated 5 days ago

Reflection_Tuning by tianyi-lab

Research paper for LLM instruction tuning via data recycling

teknium1:

winglian:

Created 3 years ago

Updated 2 years ago

data-juicer by datajuicer

Data-Juicer: Data processing system for foundation models

xiaofan-luan:

ekzhu:

chiphuyen:

CodeCreator:

Created 3 years ago

Updated 1 day ago

insanely-fast-whisper by Vaibhavs10

Fast Whisper transcription CLI

kentcdodds:

doriandarko:

jrk:

tjbck:

Created 3 years ago

Updated 11 months ago

gpt-prompt-engineer by mshumer

Prompt engineering tool for automated prompt optimization

dguido:

hammer:

gregpr07:

chiphuyen:

Created 3 years ago

Updated 11 months ago

autogen by microsoft

Agentic framework for multi-agent AI applications

wesm:

chiphuyen:

ebursztein:

gagb:

Created 3 years ago

Updated 5 months ago

OmniQuant by OpenGVLab

OmniQuant: LLM quantization research paper

Created 3 years ago

Updated 10 months ago

alignment-handbook by huggingface

Handbook for aligning language models with human/AI preferences

eugeneyan:

drishanarora:

philschmid:

vincentweisser:

Created 3 years ago

Updated 2 weeks ago

ml-engineering by stas00

Open book for LLM/VLM training engineers

tobi:

stas00:

WoosukKwon:

ppwwyyxx:

Created 6 years ago

Updated 2 days ago

metal-flash-attention by philipturner

Metal port of FlashAttention for Apple silicon

winglian:

osanseviero:

Ying1123:

tridao:

Created 3 years ago

Updated 2 years ago

llm-foundry by mosaicml

LLM training code for Databricks foundation models

hiyouga:

vincentweisser:

hammer:

Sanger2000:

Created 3 years ago

Updated 6 months ago

prompts-for-edu by microsoft

Educational prompt resource for generative AI tools

sb2nov:

jeresig:

Created 3 years ago

Updated 2 years ago

AutoGPTQ by AutoGPTQ

LLM quantization package using GPTQ algorithm

vincentweisser:

youkaichao:

chiphuyen:

osanseviero:

Created 3 years ago

Updated 1 year ago

llm-awq by mit-han-lab

Weight quantization research paper for LLM compression/acceleration

hiyouga:

chiphuyen:

lysandrejik:

hammer:

Created 3 years ago

Updated 1 year ago

neurips_llm_efficiency_challenge by llm-efficiency-challenge

Competition toolkit for efficient LLM inference on a single GPU

hiyouga:

rasbt:

artidoro:

Created 3 years ago

Updated 3 years ago

InternLM by InternLM

LLM series (InternLM, InternLM2, InternLM2.5, InternLM3) official release

hammer:

simonw:

soldni:

omarsar:

Created 3 years ago

Updated 11 months ago

magentic by jackmpcollins

SDK for integrating LLMs as Python functions using decorators

osanseviero:

didierrlopes:

ggerganov:

vanpelt:

Created 3 years ago

Updated 7 months ago

textbook_quality by VikParuchuri

Synthetic data generator for LLM pretraining

osanseviero:

philschmid:

winglian:

Created 3 years ago

Updated 3 years ago

Xwin-LM by Xwin-LM

LLM for alignment research, fine-tuning, and open-source contribution

Created 3 years ago

Updated 2 years ago

synthesizer by SciPhi-AI

LLM framework for RAG and data creation

mlejva:

shyamal-anadkat:

osanseviero:

hammer:

Created 3 years ago

Updated 2 years ago

AutoAWQ by casper-hansen

AutoAWQ is a tool for 4-bit quantized LLM inference

vincentweisser:

peakji:

WoosukKwon:

winglian:

Created 3 years ago

Updated 1 year ago

exllamav2 by turboderp-org

Inference library for running LLMs locally on consumer GPUs

tobi:

shimmyshimmer:

JustinLin610:

chiphuyen:

Created 3 years ago

Updated 7 months ago

airoboros by jondurbin

Self-instruct tool for LLM finetuning

casper-hansen:

eugeneyan:

mlabonne:

philschmid:

Created 3 years ago

Updated 2 years ago

TinyLlama by jzhang38

Tiny pretraining project for a 1.1B Llama model

karpathy:

geohot:

tobi:

chiphuyen:

Created 3 years ago

Updated 2 years ago

CTranslate2 by OpenNMT

Fast inference engine for Transformer models

merrymercy:

simonw:

eugeneyan:

bryanhelmig:

Created 7 years ago

Updated 5 days ago

promptfoo by promptfoo

CLI tool for LLM prompt/agent/RAG testing and red-teaming

didierrlopes:

transitive-bullshit:

philschmid:

marcklingen:

Created 3 years ago

Updated 10 hours ago

autofaiss by criteo

Auto indexer for k-NN similarity search using Faiss

jiamings:

simonw:

alexey-milovidov:

generall:

Created 5 years ago

Updated 11 months ago

promptsource by bigscience-workshop

Toolkit for creating, sharing, and using natural language prompts

clmnt:

chiphuyen:

teknium1:

infwinston:

Created 5 years ago

Updated 3 years ago

PaLM by conceptofmind

Open-source PaLM implementation for language model research

winglian:

transitive-bullshit:

omarsar:

JustinLin610:

Created 3 years ago

Updated 2 years ago

BLoRA by sabetAI

Inference optimization for batched LoRA adapters

winglian:

Created 3 years ago

Updated 3 years ago

qlora by artidoro

Finetuning tool for quantized LLMs

tobi:

chiphuyen:

vincentweisser:

artidoro:

Created 3 years ago

Updated 2 years ago

hydra-moe by SkunkworksAI

MoE framework for scaling language models, aiming for GPT-4 level performance

Created 3 years ago

Updated 2 years ago

GPTeacher by teknium1

GPT-4 generated datasets for instruction tuning

osanseviero:

omarsar:

jn2clark:

winglian:

Created 3 years ago

Updated 3 years ago

EdgeGPT by acheong08

Reverse-engineered API for Microsoft Bing Chat (archived)

winglian:

Created 3 years ago

Updated 3 years ago

llama-cookbook by meta-llama

Guide for building with Llama models

alexchen4ai:

didierrlopes:

transitive-bullshit:

ValentaTomas:

Created 3 years ago

Updated 4 months ago

prm800k by openai

Dataset of LLM solutions to math problems with step-level correctness labels

hiyouga:

Jiayi-Pan:

pgarbacki:

transitive-bullshit:

Created 3 years ago

Updated 3 years ago

chain-of-thought-hub by FranxYao

LLM benchmark for complex reasoning via chain-of-thought prompting

hammer:

infwinston:

transitive-bullshit:

JustinLin610:

Created 3 years ago

Updated 2 years ago

codeinterpreter-api by shroominic

LangChain implementation of ChatGPT Code Interpreter

JohannesHa:

dharmeshs:

transitive-bullshit:

hwchase17:

Created 3 years ago

Updated 1 year ago

GPT-4-LLM by Instruction-Tuning-with-GPT-4

GPT-4 data for instruction-tuning LLMs via supervised/RL

gakonst:

marcklingen:

teknium1:

hammer:

Created 3 years ago

Updated 3 years ago

Lemur by OpenLemur

Open language model for language agents

osanseviero:

huybery:

hiyouga:

dzhulgakov:

Created 3 years ago

Updated 2 years ago

open-instruct by allenai

Training codebase for instruction-following language models

hammer:

zhyncs:

vincentweisser:

RJT1990:

Created 3 years ago

Updated 8 hours ago

flexflow-train by flexflow

Accelerating distributed deep learning training

parano:

Edward-Sun:

NikolaBorisov:

osanseviero:

Created 7 years ago

Updated 3 days ago

llm-attacks by llm-attacks

Attack framework for aligned LLMs, based on a research paper

ebursztein:

chiphuyen:

hiyouga:

merrymercy:

Created 3 years ago

Updated 2 years ago

BlingFire by microsoft

Fast text tokenization library

ankane:

soldni:

ekzhu:

hammer:

Created 7 years ago

Updated 1 year ago

Platypus by arielnlee

Code for fine-tuning LLMs using LoRA

eugeneyan:

pgarbacki:

mlabonne:

Created 3 years ago

Updated 2 years ago

UltraChat by thunlp

Multi-round dialogue dataset and models for chat language model training

winglian:

teknium1:

hiyouga:

Created 3 years ago

Updated 2 years ago

rerope by bojone

Position embeddings research paper

winglian:

Ying1123:

merrymercy:

Created 3 years ago

Updated 2 years ago

ragas by vibrantlabsai

Toolkit for LLM application evaluation

gregpr07:

alexchen4ai:

hiyouga:

nirga:

Created 3 years ago

Updated 7 months ago

curated-transformers by explosion

PyTorch library for composable Transformer models

simonw:

rromb:

millionintegrals:

lantiga:

Created 4 years ago

Updated 2 years ago

outlines by dottxt-ai

SDK for structured LLM text generation

tobi:

kerollmops:

willingc:

jn2clark:

Created 3 years ago

Updated 2 weeks ago

FlexLLMGen by FMInference

High-throughput generation engine for LLMs with limited GPU memory

chiphuyen:

jrk:

parano:

luiscape:

Created 3 years ago

Updated 1 year ago

deep-learning-pytorch-huggingface by philschmid

Tutorials for deep learning with PyTorch and Hugging Face libraries

vincentweisser:

pgarbacki:

Created 3 years ago

Updated 1 year ago

deduplicate-text-datasets by google-research

Rust CLI tool for language model dataset deduplication

bryanhelmig:

hammer:

mfuntowicz:

Created 5 years ago

Updated 2 years ago

twitter-api-client by trevorhobenshield

Python SDK for X/Twitter API access, scraping, and automation

tobi:

transitive-bullshit:

Created 3 years ago

Updated 2 years ago

alpaca_farm by tatsu-lab

RLHF simulation framework for accessible instruction-following/alignment research

chiphuyen:

pgarbacki:

pirroh:

teknium1:

Created 3 years ago

Updated 2 years ago

openchat by imoneoi

Open-source LLM fine-tuned with C-RLFT, inspired by offline reinforcement learning

vincentweisser:

philschmid:

chiphuyen:

transitive-bullshit:

Created 3 years ago

Updated 2 years ago

txtai by neuml

All-in-one AI framework for semantic search, LLM orchestration, and language model workflows

tobi:

chiphuyen:

paul-gauthier:

ishaan-jaff:

Created 6 years ago

Updated 1 day ago

LLM-Training-Puzzles by srush

Hands-on puzzles for large language model training

Jiayi-Pan:

albertfgu:

willccbb:

hiyouga:

Created 3 years ago

Updated 2 years ago

instructor by 567-labs

SDK for structured LLM outputs using Pydantic models

cournape:

gregpr07:

jxnl:

willccbb:

Created 3 years ago

Updated 2 days ago

LMFlow by OptimalScale

Toolkit for finetuning and inference of large foundation models

tobi:

shizhediao:

ebursztein:

zhuohan123:

Created 3 years ago

Updated 2 months ago

exllama by turboderp

Llama implementation for memory-efficient quantized weights

tobi:

parano:

lantiga:

bryanhelmig:

Created 3 years ago

Updated 3 years ago

text-generation-inference by huggingface

Rust/Python/gRPC server for fast LLM text generation

tobi:

clmnt:

tjbck:

chiphuyen:

Created 4 years ago

Updated 6 months ago

vllm by vllm-project

LLM serving engine for high-throughput, memory-efficient inference

karpathy:

clmnt:

tobi:

adamdotdevin:

Created 3 years ago

Updated 12 hours ago

Sophia by Liuhong99

Optimizer for language model pre-training (research paper)

chiphuyen:

vincentweisser:

eiso:

hiyouga:

Created 3 years ago

Updated 2 years ago

simpleaichat by minimaxir

Python SDK for streamlined chat app integration (ChatGPT, GPT-4)

ishaan-jaff:

ogabrielluiz:

rodrigosnader:

luiscape:

Created 3 years ago

Updated 2 years ago

CodeTF by salesforce

Transformer library for code LLMs and code intelligence tasks

AntonOsika:

wsxiaoys:

hammer:

Created 3 years ago

Updated 1 year ago

Mr.-Ranedeer-AI-Tutor by JushBJJ

GPT-4 prompt for personalized learning

parano:

torantulino:

ValentaTomas:

swyxio:

Created 3 years ago

Updated 1 year ago

WizardLM by nlpxucan

LLMs built using Evol-Instruct for complex instruction following

vincentweisser:

chiphuyen:

WoosukKwon:

ishaan-jaff:

Created 3 years ago

Updated 1 year ago

aider by Aider-AI

AI pair programming in your terminal

bcherny:

nat:

hammer:

ekzhu:

Created 3 years ago

Updated 4 months ago

developer by smol-ai

Agent for embedding a developer in your app

vanpelt:

chiphuyen:

shyamal-anadkat:

mchiang0610:

Created 3 years ago

Updated 2 years ago

guidance by guidance-ai

Guidance is a programming paradigm for steering LLMs

tobi:

ekzhu:

stas00:

Ying1123:

Created 3 years ago

Updated 4 months ago

LLMsPracticalGuide by Mooler0410

Curated list of LLM practical guide resources (tree, examples, papers)

eugeneyan:

swyxio:

ogabrielluiz:

hiyouga:

Created 3 years ago

Updated 6 months ago

godot-dodo by minosvasilias

Pipeline for finetuning language models on GDScript code

sb2nov:

alexanderatallah:

Created 3 years ago

Updated 3 years ago

dspy by stanfordnlp

Framework for programming language models, not prompting

tobi:

mateiz:

vincentweisser:

pgarbacki:

Created 3 years ago

Updated 1 day ago

web-llm by mlc-ai

In-browser LLM inference engine using WebGPU for hardware acceleration

tobi:

mholt:

didierrlopes:

doriandarko:

Created 3 years ago

Updated 1 week ago

gpt4all by nomic-ai

Desktop app for local LLM inference, no GPU/API needed

willingc:

zhiyuan8:

osanseviero:

antirez:

Created 3 years ago

Updated 1 year ago

ColossalAI by hpcaitech

AI system for large-scale parallel training

tobi:

hammer:

thinkall:

chiphuyen:

Created 5 years ago

Updated 11 hours ago

ChatPaper by kaixindelele

AI tool for summarizing arXiv papers using ChatGPT

geekan:

omarsar:

Created 3 years ago

Updated 7 months ago

GPTQ-for-LLaMa by qwopqwop200

4-bit quantization for LLaMA models using GPTQ

chiphuyen:

gakonst:

hiyouga:

soldni:

Created 3 years ago

Updated 2 years ago

alpaca-lora by tloen

LoRA fine-tuning for LLaMA

JustinLin610:

vincentweisser:

nirga:

chiphuyen:

Created 3 years ago

Updated 2 years ago

flan-alpaca by declare-lab

Instruction tuning code extends synthetic training

Created 3 years ago

Updated 3 years ago

MiniChain by srush

Tiny library for coding with large language models

soldni:

hiyouga:

lysandrejik:

ValentaTomas:

Created 3 years ago

Updated 2 years ago

alpaca_lora_4bit by johnsmith0031

Fine-tuning and inference tool for quantized LLaMA models

pgarbacki:

winglian:

Created 3 years ago

Updated 2 years ago

AlpacaDataCleaned by gururise

Cleaned dataset for Alpaca LLM training

tobi:

osanseviero:

JustinLin610:

winglian:

Created 3 years ago

Updated 7 months ago

lex-gpt by rlancemartin

AI-powered search for the Lex Fridman podcast

hammer:

sualehasif:

vanpelt:

Created 3 years ago

Updated 3 years ago

examples by mosaicml

Reference benchmarks for training and deploying ML models at scale

hammer:

jfrankle:

soldni:

hanlint:

Created 4 years ago

Updated 6 months ago

trafilatura by adbar

Python package for web text extraction

thinkall:

simonw:

philschmid:

Created 7 years ago

Updated 3 days ago

cleanlab by cleanlab

Data-centric AI package for ML with messy data

chiphuyen:

alexanderatallah:

transitive-bullshit:

simonw:

Created 8 years ago

Updated 8 months ago

llama_index by run-llama

Data framework for building LLM-powered agents

karpathy:

willingc:

atroyn:

zhuohan123:

Created 3 years ago

Updated 1 day ago

textgen by oobabooga

Web UI for LLM text generation

danielhanchen:

vincentweisser:

shimmyshimmer:

soumith:

Created 3 years ago

Updated 1 month ago

FasterTransformer by NVIDIA

Optimized transformer library for inference

nat:

chiphuyen:

JustinLin610:

mfuntowicz:

Created 5 years ago

Updated 2 years ago

ControlNet by lllyasviel

Neural network structure for adding conditional control to diffusion models

vincentweisser:

codekansas:

louisgv:

ogabrielluiz:

Created 3 years ago

Updated 2 years ago

lora by cloneofsimo

LoRA tool for fast diffusion fine-tuning

vincentweisser:

jn2clark:

swyxio:

eugeneyan:

Created 3 years ago

Updated 2 years ago

GPTZero by BurhanUlTayyab

Open-source implementation of GPTZero

Created 3 years ago

Updated 5 months ago

flash-attention by Dao-AILab

Fast, memory-efficient attention implementation

karpathy:

Jiayi-Pan:

zhiyuan8:

alexchen4ai:

Created 4 years ago

Updated 3 days ago

nanoGPT by karpathy

Minimalist repo for training/finetuning GPT models

tobi:

danielgross:

chiphuyen:

ankane:

Created 3 years ago

Updated 11 months ago

setfit by huggingface

Few-shot learning framework for Sentence Transformers

clmnt:

luiscape:

patrickvonplaten:

transitive-bullshit:

Created 4 years ago

Updated 3 days ago

improved-diffusion by openai

Image diffusion codebase for research

aravindsrinivas:

patrickvonplaten:

Created 5 years ago

Updated 2 years ago

v-diffusion-pytorch by crowsonkb

PyTorch code for v-objective diffusion model inference

chenlin9:

patrickvonplaten:

luiscape:

lucidrains:

Created 4 years ago

Updated 3 years ago

RePaint by andreas128

Image inpainting via denoising diffusion probabilistic models

patrickvonplaten:

Created 4 years ago

Updated 4 years ago

clip-interrogator by pharmapsychotic

Image-to-prompt tool for text-to-image models

hiyouga:

jn2clark:

chuanli11:

osanseviero:

Created 4 years ago

Updated 2 years ago

ai-notes by swyxio

AI engineering notes for software engineers

AntonOsika:

shyamal-anadkat:

quincylarson:

ValentaTomas:

Created 4 years ago

Updated 7 months ago

open_clip by mlfoundations

OpenCLIP: open-source CLIP implementation for vision-language representation learning

ekzhang:

jeresig:

c4pt0r:

taranjeet:

Created 5 years ago

Updated 1 week ago

LAVIS by salesforce

Library for language-vision AI research

chiphuyen:

simonw:

transitive-bullshit:

Edward-Sun:

Created 4 years ago

Updated 3 weeks ago

img2dataset by rom1504

CLI tool for creating large image datasets from URLs

winglian:

aangelopoulos:

lucidrains:

jn2clark:

Created 5 years ago

Updated 11 months ago

diffusers by huggingface

PyTorch/Flax library for diffusion model research and applications

karpathy:

clmnt:

vincentweisser:

hammer:

Created 4 years ago

Updated 19 hours ago

Dreambooth-Stable-Diffusion by XavierXiao

Dreambooth implementation for Stable Diffusion

tjbck:

omarsar:

transitive-bullshit:

wongmjane:

Created 4 years ago

Updated 3 years ago

k-diffusion by crowsonkb

PyTorch implementation of Karras et al. (2022) diffusion models

jiamings:

parano:

luiscape:

wongmjane:

Created 4 years ago

Updated 7 months ago

nn-zero-to-hero by karpathy

Educational resource for neural network development, from basics to advanced models

norvig:

zhiyuan8:

didierrlopes:

omarsar:

Created 4 years ago

Updated 2 years ago

upscayl by upscayl

AI image upscaler app for Linux, macOS, and Windows

mudler:

luiscape:

chiphuyen:

taranjeet:

Created 4 years ago

Updated 4 days ago

silero-models by snakers4

Pre-trained STT/TTS/text-enhancement models made simple

luiscape:

generall:

Created 6 years ago

Updated 2 months ago

RWKV-LM by BlinkDL

RNN for LLM, transformer-level performance, parallelizable training

geohot:

danielgross:

nat:

sxyu:

Created 5 years ago

Updated 1 week ago

browser-ml-inference by jobergum

React app for text emotion prediction using browser-based ML inference

sirupsen:

philschmid:

Created 4 years ago

Updated 4 years ago

x-transformers by lucidrains

Transformer library with extensive experimental features

chiphuyen:

hammer:

chenlin9:

Jiayi-Pan:

Created 6 years ago

Updated 5 days ago

Feedback? Help us improve.