Clement Delangue

Cofounder of Hugging Face

Starred Projects (48)

ml-intern by huggingface

AI engineer for autonomous ML research, training, and deployment

luiscape:

vincentweisser:

JohannesHa:

hammer:

Created 10 months ago

Updated 2 days ago

hf-agents by huggingface

Local coding agent with hardware-aware LLM deployment

Created 5 months ago

Updated 5 months ago

Open-Claude-Cowork by DevAgentForge

Desktop AI collaboration partner for complex tasks

lewtun:

teknium1:

Created 8 months ago

Updated 5 months ago

skills by huggingface

Agent context definitions for AI/ML workflows

JustinLin610:

thinkall:

shizhediao:

omarsar:

Created 9 months ago

Updated 1 day ago

OpenEnv by huggingface

Framework for agentic RL training environments

didierrlopes:

luiscape:

shizhediao:

mlejva:

Created 11 months ago

Updated 1 day ago

reachy_mini by pollen-robotics

SDK for controlling an expressive robot

abhishekkrthakur:

lysandrejik:

ogabrielluiz:

Created 1 year ago

Updated 21 hours ago

trackio by gradio-app

Lightweight experiment tracking for ML workflows

vanpelt:

hammer:

hiyouga:

lvwerra:

Created 1 year ago

Updated 1 day ago

observers by cfahlgren1

Lightweight library for AI observability

thomwolf:

philschmid:

Created 1 year ago

Updated 1 year ago

optimum-neuron by huggingface

Transformers training and inference acceleration for AWS accelerators

luiscape:

philschmid:

Created 3 years ago

Updated 1 day ago

transformers.js by huggingface

Run Transformers models directly in your browser

tjbck:

ankane:

doriandarko:

mckaywrigley:

Created 3 years ago

Updated 1 day ago

evaluation-guidebook by huggingface

LLM evaluation guide for practitioners

winglian:

thomwolf:

dguido:

stas00:

Created 1 year ago

Updated 9 months ago

refiners by finegrain-ai

Microframework for foundation model adaptation using PyTorch

luiscape:

Created 3 years ago

Updated 11 months ago

mergoo by Leeroo-AI

Library for merging LLM experts and training merged models

philschmid:

mlabonne:

Created 2 years ago

Updated 2 years ago

nanotron by huggingface

Minimalistic library for large language model pretraining

shizhediao:

vincentweisser:

luiscape:

casper-hansen:

Created 3 years ago

Updated 3 months ago

distil-whisper by huggingface

Distilled speech recognition model, a faster Whisper variant

transitive-bullshit:

luiscape:

thomwolf:

ogabrielluiz:

Created 2 years ago

Updated 1 year ago

vllm by vllm-project

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

karpathy:

tobi:

adamdotdevin:

willingc:

Created 3 years ago

Updated 11 hours ago

transformers by huggingface

ML library for pretrained model inference and training

lilianweng:

karpathy:

tjbck:

patrickvonplaten:

Created 7 years ago

Updated 4 hours ago

bloomz.cpp by nmntz

C++ project for BLOOM model inference

lewtun:

antirez:

transitive-bullshit:

generall:

Created 3 years ago

Updated 3 years ago

huggingface.js by huggingface

JS utils for Hugging Face Hub API interaction

abidlabs:

ggerganov:

thomwolf:

osanseviero:

Created 3 years ago

Updated 2 days ago

text-generation-inference by huggingface

Rust/Python/gRPC server for fast LLM text generation

tobi:

tjbck:

chiphuyen:

stas00:

Created 3 years ago

Updated 5 months ago

Gauss by justjake

macOS app for local Stable Diffusion image generation

gakonst:

antirez:

jrk:

cchio:

Created 3 years ago

Updated 3 years ago

speechbox by huggingface

Speech processing tools (punctuation, diarization)

philschmid:

osanseviero:

lewtun:

patrickvonplaten:

Created 3 years ago

Updated 2 years ago

stable-diffusion-webui by AUTOMATIC1111

Web UI for Stable Diffusion

jmorganca:

k06a:

vincentweisser:

tjbck:

Created 4 years ago

Updated 6 months ago

setfit by huggingface

Few-shot learning framework for Sentence Transformers

luiscape:

patrickvonplaten:

transitive-bullshit:

jph00:

Created 4 years ago

Updated 2 days ago

pytorch-image-models by huggingface

PyTorch image model collection with training, eval, and inference scripts

karpathy:

osanseviero:

Jiayi-Pan:

thomwolf:

Created 7 years ago

Updated 1 day ago

diffusers by huggingface

PyTorch/Flax library for diffusion model research and applications

karpathy:

vincentweisser:

hammer:

chiphuyen:

Created 4 years ago

Updated 1 day ago

evaluate by huggingface

ML model evaluation library for standardized performance reporting

chiphuyen:

natolambert:

lvwerra:

hammer:

Created 4 years ago

Updated 2 months ago

gradio by gradio-app

Python SDK for interactive ML web applications

willingc:

gregpr07:

shimmyshimmer:

vincentweisser:

Created 7 years ago

Updated 3 hours ago

promptsource by bigscience-workshop

Toolkit for creating, sharing, and using natural language prompts

chiphuyen:

jph00:

teknium1:

infwinston:

Created 5 years ago

Updated 2 years ago

bigscience by bigscience-workshop

Large-scale LLM training and scaling infrastructure

vincentweisser:

JohannesHa:

hammer:

osanseviero:

Created 5 years ago

Updated 2 years ago

optimum by huggingface

Hardware optimization tools for Transformers, Diffusers, etc

PiotrDabkowski:

ankane:

soldni:

julien-c:

Created 5 years ago

Updated 2 weeks ago

mistral by stanford-crfm

Framework for large language model training

osanseviero:

infwinston:

parasj:

patrickvonplaten:

Created 5 years ago

Updated 6 months ago

accelerate by huggingface

PyTorch training helper for distributed execution

chiphuyen:

eugeneyan:

pgarbacki:

ogabrielluiz:

Created 5 years ago

Updated 1 day ago

nn_pruning by huggingface

Model pruning tool for efficient inference

thomwolf:

Timoeller:

luiscape:

n1t0:

Created 5 years ago

Updated 4 years ago

pytorch_block_sparse by huggingface

PyTorch extension for block-sparse linear layers

parasj:

lucidrains:

lewtun:

shizhediao:

Created 6 years ago

Updated 5 years ago

minGPT by karpathy

Minimal PyTorch re-implementation for GPT training and inference

aravindsrinivas:

nat:

geohot:

lilianweng:

Created 6 years ago

Updated 2 years ago

datasets by huggingface

Access and process large AI datasets efficiently

chiphuyen:

transitive-bullshit:

gakonst:

hiyouga:

Created 6 years ago

Updated 20 hours ago

tokenizers by huggingface

Fast tokenizer library optimized for research and production

hammer:

syrusakbary:

transitive-bullshit:

JohannesHa:

Created 6 years ago

Updated 1 day ago

BERT-of-Theseus by JetRunner

PyTorch code for BERT compression via progressive module replacement

lysandrejik:

guoday:

Created 6 years ago

Updated 3 years ago

node-question-answering by huggingface

Fast question answering for Node.js

chuanli11:

srush:

luiscape:

julien-c:

Created 6 years ago

Updated 3 years ago

rust-bert by guillaume-be

Rust SDK for transformer-based NLP, porting Hugging Face models

hurshagrawal:

transitive-bullshit:

lewtun:

generall:

Created 6 years ago

Updated 8 months ago

tflite-android-transformers by huggingface

Android demo apps for on-device Transformer inference via TensorFlow Lite

lysandrejik:

Created 6 years ago

Updated 3 years ago

GPT2-Chinese by Morizeyao

GPT2 training code for Chinese language models

shizhediao:

Created 7 years ago

Updated 2 years ago

bertviz by jessevig

Interactive tool for visualizing attention in Transformer language models

chiphuyen:

vincentweisser:

borzunov:

osanseviero:

Created 7 years ago

Updated 8 months ago

swift-coreml-transformers by huggingface

Swift Core ML implementations of Transformer models

osanseviero:

luiscape:

hammer:

iamtrask:

Created 7 years ago

Updated 2 years ago

naacl_transfer_learning_tutorial by huggingface

NLP transfer learning tutorial code

hiyouga:

julien-c:

hammer:

soumith:

Created 7 years ago

Updated 7 years ago

transfer-learning-conv-ai by huggingface

Conversational AI code for transfer learning research

huybery:

vincentweisser:

codekansas:

stas00:

Created 7 years ago

Updated 3 years ago

pytorch-openai-transformer-lm by huggingface

PyTorch implementation of OpenAI's Transformer LM

lysandrejik:

thomwolf:

nottombrown:

omarsar:

Created 8 years ago

Updated 5 years ago

Feedback? Help us improve.