Alex Chen

Cofounder of Nexa AI

Starred Projects (53)

unsloth by unslothai

Finetuning tool for LLMs, targeting speed and memory efficiency

tobi:

karpathy:

danielhanchen:

shimmyshimmer:

Created 2 years ago

Updated 23 hours ago

LLaMA-Factory by hiyouga

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

patrickvonplaten:

teetone:

lysandrejik:

gregpr07:

Created 2 years ago

Updated 1 day ago

nexa-sdk by NexaAI

Nexa SDK: local inference framework for GGML/ONNX models

zhiyuan8:

dynamicwebpaige:

Created 1 year ago

Updated 2 days ago

higgs-audio by boson-ai

Expressive text-to-audio generation model

jiamings:

hiyouga:

Created 4 months ago

Updated 2 months ago

Anemll by Anemll

Framework for porting LLMs to Apple Neural Engine (ANE)

luiscape:

AlexCheema:

Created 10 months ago

Updated 2 weeks ago

Olive by microsoft

AI model optimization toolkit for ONNX Runtime

hammer:

philschmid:

Created 6 years ago

Updated 1 week ago

candle by huggingface

Minimalist ML framework for Rust, emphasizing performance and ease of use

tobi:

binarybana:

jn2clark:

developit:

Created 2 years ago

Updated 5 days ago

MiMo by XiaomiMiMo

LLM for reasoning, pre-trained and post-trained for math/code tasks

WoosukKwon:

zhyncs:

omarsar:

Created 7 months ago

Updated 5 months ago

mllm by UbiquitousLearning

Mobile inference engine for multimodal LLMs

zhiyuan8:

Created 2 years ago

Updated 1 day ago

edge by cartesia-ai

Open-source library for efficient state space models (SSMs) on-device

Created 1 year ago

Updated 8 months ago

misaki by hexgrad

G2P engine for Kokoro models

Created 10 months ago

Updated 3 months ago

stable-diffusion.cpp by leejet

C/C++ inference for Stable Diffusion models

tobi:

andreasjansson:

antirez:

alexey-milovidov:

Created 2 years ago

Updated 1 day ago

kokoro by hexgrad

TTS inference library for Kokoro-82M

dps:

simonw:

Created 10 months ago

Updated 3 months ago

mlx by ml-explore

Array framework for machine learning on Apple silicon

geohot:

karpathy:

jmorganca:

chiphuyen:

Created 2 years ago

Updated 4 days ago

dia by nari-labs

TTS model for ultra-realistic dialogue generation

shimmyshimmer:

omarsar:

zhyncs:

codekansas:

Created 7 months ago

Updated 1 week ago

llama-cookbook by meta-llama

Guide for building with Llama models

didierrlopes:

transitive-bullshit:

ValentaTomas:

peakji:

Created 2 years ago

Updated 3 weeks ago

csm by SesameAILabs

Speech generation model for conversational AI research

amin3141:

thomwolf:

spelsbergsam:

dguido:

Created 9 months ago

Updated 6 months ago

Qwen2.5-Omni by QwenLM

Multimodal model for text, audio, vision, and video processing with real-time speech generation

omarsar:

jn2clark:

luiscape:

JustinLin610:

Created 8 months ago

Updated 5 months ago

python-sdk by modelcontextprotocol

Python SDK for Model Context Protocol (MCP) servers/clients

ValentaTomas:

hiyouga:

simonw:

eugeneyan:

Created 1 year ago

Updated 2 days ago

chatglm.cpp by li-plus

C++ project for ChatGLM & GLM model inference

ggerganov:

Created 2 years ago

Updated 1 year ago

mamba by state-spaces

Mamba SSM architecture for sequence modeling

geohot:

luiscape:

zhiyuan8:

shizhediao:

Created 2 years ago

Updated 2 weeks ago

MoBA by MoonshotAI

Research paper introducing MoBA for long-context LLMs

didierrlopes:

Created 9 months ago

Updated 8 months ago

AIOS by agiresearch

AI agent OS for LLM development and deployment

chuanli11:

transitive-bullshit:

omarsar:

timsuchanek:

Created 1 year ago

Updated 6 days ago

NeMo by NVIDIA-NeMo

Scalable generative AI framework for LLMs, multimodal, and speech AI research

Ying1123:

shizhediao:

robinjhuang:

tjbck:

Created 6 years ago

Updated 2 days ago

optimum-benchmark by huggingface

Benchmarking utility for Transformers, Diffusers, and other models

hammer:

Created 2 years ago

Updated 2 months ago

DeepEP by deepseek-ai

Expert-parallel communication library for MoE, targeting high-throughput and low-latency

parano:

JustinLin610:

CodeCreator:

zhyncs:

Created 9 months ago

Updated 6 days ago

EasyR1 by hiyouga

RL training framework for multi-modality models

shizhediao:

Created 9 months ago

Updated 3 days ago

chroma by chroma-core

Open-source embedding database for building LLM apps with memory

tobi:

hugs:

kiwicopple:

azayarni:

Created 3 years ago

Updated 2 days ago

quivr by QuivrHQ

RAG framework for GenAI app integration

handotdev:

osanseviero:

dguido:

mchiang0610:

Created 2 years ago

Updated 4 months ago

open-r1 by huggingface

SDK for reproducing DeepSeek-R1

chiphuyen:

hammer:

vincentweisser:

shizhediao:

Created 10 months ago

Updated 6 days ago

ollama by ollama

CLI tool for running LLMs locally

tobi:

jmorganca:

domoritz:

ekzhu:

Created 2 years ago

Updated 1 day ago

cuda-course by Infatoshi

CUDA course materials

Created 1 year ago

Updated 3 weeks ago

Agent-S by simular-ai

Agentic framework for autonomous computer interaction

chiphuyen:

omarsar:

rstojnic:

Created 1 year ago

Updated 1 month ago

coconut by facebookresearch

Research paper implementation for LLM reasoning in latent space

winglian:

hiyouga:

teknium1:

Created 10 months ago

Updated 3 months ago

flute by HanGuo97

Engine for LUT-quantized LLMs

Created 1 year ago

Updated 7 months ago

deepcompressor by nunchaku-tech

Model compression toolbox for LLMs and diffusion models

zhiyuan8:

merrymercy:

Created 1 year ago

Updated 3 months ago

nunchaku by nunchaku-tech

High-performance 4-bit diffusion model inference engine

luiscape:

parano:

chiphuyen:

jaretburkett:

Created 1 year ago

Updated 1 week ago

ragas by vibrantlabsai

Toolkit for LLM application evaluation

gregpr07:

hiyouga:

nirga:

simonw:

Created 2 years ago

Updated 2 days ago

ao by pytorch

PyTorch library for quantization and sparsity in training/inference

danielhanchen:

shimmyshimmer:

parano:

willccbb:

Created 2 years ago

Updated 23 hours ago

flash-attention by Dao-AILab

Fast, memory-efficient attention implementation

karpathy:

Jiayi-Pan:

zhiyuan8:

gakonst:

Created 3 years ago

Updated 5 days ago

Megatron-LM by NVIDIA

Framework for training transformer models at scale

jiamings:

gravicle:

parasj:

vincentweisser:

Created 6 years ago

Updated 21 hours ago

bitsandbytes by bitsandbytes-foundation

PyTorch library for k-bit quantization, enabling accessible LLMs

tjbck:

danielhanchen:

shimmyshimmer:

eugeneyan:

Created 4 years ago

Updated 4 days ago

Local-File-Organizer by QiuYannnn

AI-powered file management tool for local organization

omarsar:

pirroh:

dguido:

Created 1 year ago

Updated 1 year ago

qwen.cpp by QwenLM

C++ project for Qwen-LM inference (now integrated into llama.cpp)

ggerganov:

bratseth:

JustinLin610:

osanseviero:

Created 2 years ago

Updated 11 months ago

Awesome-LLM-Quantization by pprp

Curated list of resources for LLM quantization research

Created 1 year ago

Updated 1 month ago

ggml by ggml-org

Tensor library for machine learning

tunguz:

zhiyuan8:

hugs:

mckaywrigley:

Created 3 years ago

Updated 6 days ago

LLaMA-Omni by ictnlp

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

jph00:

omarsar:

Created 1 year ago

Updated 6 months ago

SuperPrompt by NeoVertex1

Prompt engineering research for AI agent understanding

willccbb:

pgarbacki:

bryanhelmig:

Created 1 year ago

Updated 2 months ago

Qwen by QwenLM

Chat & pretrained LLM by Alibaba Cloud

spartee:

shimmyshimmer:

omarsar:

shizhediao:

Created 2 years ago

Updated 4 days ago

Awesome-LLMs-on-device by NexaAI

Survey of on-device LLMs, architectures, and optimization

zhiyuan8:

Created 1 year ago

Updated 10 months ago

trl by huggingface

Library for transformer RL

jeffchuber:

vincentweisser:

tjbck:

willccbb:

Created 5 years ago

Updated 2 days ago

open_lm by mlfoundations

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

shizhediao:

vincentweisser:

jph00:

hammer:

Created 2 years ago

Updated 5 months ago

octopus-v4 by NexaAI

Graph of language models for connecting specialized AI

zhiyuan8:

alexanderatallah:

Created 1 year ago

Updated 1 year ago

Feedback? Help us improve.