Daniel Han

Cofounder of Unsloth

Starred Projects (72)

cua by trycua

AI agent framework for computer OS control in virtual containers

tobi:

dguido:

ekzhu:

ValentaTomas:

Created 1 year ago

Updated 13 hours ago

textgen by oobabooga

Web UI for LLM text generation

vincentweisser:

shimmyshimmer:

soumith:

doriandarko:

Created 3 years ago

Updated 1 month ago

Jackrong-llm-finetuning-guide by R6410418

End-to-end LLM fine-tuning pipeline for accessible AI model adaptation

shimmyshimmer:

Created 3 months ago

Updated 17 hours ago

ATLAS by itigges22

Boosts frozen LLM performance for efficient, self-hosted AI

winglian:

dguido:

Created 5 months ago

Updated 1 day ago

mlx-tune by ARahim3

LLM fine-tuning prototype for Mac users

w4nderlust:

shimmyshimmer:

Created 6 months ago

Updated 2 weeks ago

executorch by pytorch

On-device AI framework for PyTorch inference and training

patrickvonplaten:

ebursztein:

shimmyshimmer:

luiscape:

Created 4 years ago

Updated 18 hours ago

unsloth by unslothai

Finetuning tool for LLMs, targeting speed and memory efficiency

tobi:

karpathy:

alexchen4ai:

shimmyshimmer:

Created 2 years ago

Updated 13 hours ago

OpenEnv by huggingface

Framework for agentic RL training environments

clmnt:

didierrlopes:

luiscape:

shizhediao:

Created 9 months ago

Updated 23 hours ago

ao by pytorch

PyTorch library for quantization and sparsity in training/inference

shimmyshimmer:

parano:

willccbb:

alexchen4ai:

Created 2 years ago

Updated 1 day ago

gpt-oss by openai

Open-weight LLMs for reasoning and agents

karpathy:

borzunov:

chiphuyen:

transitive-bullshit:

Created 1 year ago

Updated 1 month ago

cactus by cactus-compute

Framework for on-device AI, targeting mobile and wearables

parano:

shimmyshimmer:

timsuchanek:

thomwolf:

Created 1 year ago

Updated 1 day ago

openai-imo-2025-proofs by aw31

LLM-generated proofs for math olympiads

JohannesHa:

Created 11 months ago

Updated 11 months ago

transformers-qwen3-moe-fused by woct0rdho

Optimized MoE training for large language models

hiyouga:

Created 1 year ago

Updated 4 months ago

notebooks by unslothai

Collection of fine-tuning notebooks for Colab/Kaggle

abidlabs:

omarsar:

shimmyshimmer:

Created 1 year ago

Updated 16 hours ago

vllm by vllm-project

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

karpathy:

clmnt:

tobi:

adamdotdevin:

Created 3 years ago

Updated 13 hours ago

ART by OpenPipe

RL library for training LLM agents via GRPO

swyxio:

rotemweiss57:

lewtun:

luiscape:

Created 1 year ago

Updated 19 hours ago

synthetic-data-kit by meta-llama

Synthetic data CLI tool for LLM fine-tuning

chiphuyen:

shimmyshimmer:

Created 1 year ago

Updated 8 months ago

void by voideditor

Open-source code editor alternative

chiphuyen:

gregpr07:

omarsar:

wongmjane:

Created 1 year ago

Updated 1 month ago

airweave by airweave-ai

Semantic MCP server for AI agents

ogabrielluiz:

assafelovic:

chiphuyen:

gregpr07:

Created 1 year ago

Updated 1 month ago

ollama by ollama

CLI tool for running LLMs locally

tobi:

willingc:

didierrlopes:

jmorganca:

Created 3 years ago

Updated 1 day ago

Kiln by Kiln-AI

AI prototyping and dataset collaboration tool

chiphuyen:

hiyouga:

Created 1 year ago

Updated 22 hours ago

memory by facebookresearch

Reference implementation for memory layers research paper

Created 1 year ago

Updated 1 year ago

unsloth-zoo by unslothai

Accelerate LLM finetuning with reduced VRAM usage

shimmyshimmer:

Created 1 year ago

Updated 16 hours ago

llama.cpp by ggml-org

C/C++ library for local LLM inference

karpathy:

nat:

tobi:

hiyouga:

Created 3 years ago

Updated 1 day ago

lectures by gpu-mode

Lecture series for GPU-accelerated computing

cournape:

stas00:

xiezhq-hermann:

willccbb:

Created 2 years ago

Updated 3 weeks ago

sglang by sgl-project

Fast serving framework for LLMs and vision language models

amin3141:

shimmyshimmer:

beyang:

samlambert:

Created 2 years ago

Updated 14 hours ago

open-instruct by allenai

Training codebase for instruction-following language models

hammer:

zhyncs:

vincentweisser:

RJT1990:

Created 3 years ago

Updated 23 hours ago

bitsandbytes by bitsandbytes-foundation

PyTorch library for k-bit quantization, enabling accessible LLMs

lysandrejik:

tjbck:

alexchen4ai:

shimmyshimmer:

Created 5 years ago

Updated 1 day ago

patchwork by patched-codes

CLI tool for enterprise workflow automation using agentic AI

gregpr07:

samuelcolvin:

shyamal-anadkat:

taranjeet:

Created 2 years ago

Updated 1 day ago

mem0 by mem0ai

AI agent memory layer for personalized interactions

anurag:

amin3141:

xiezhq-hermann:

gregpr07:

Created 3 years ago

Updated 1 day ago

heroui by heroui-inc

I am sorry, but I cannot access the content of the GitHub repository or its README file using the provided information and the available tools. Therefore, I am unable to generate the requested summary. Please provide a direct URL to the README content if you would like me to summarize it

smthomas:

deshraj:

shimmyshimmer:

hammer:

Created 5 years ago

Updated 17 hours ago

textgrad by zou-group

Autograd engine for textual gradients, enabling LLM-driven optimization

ekzhu:

chiphuyen:

Created 2 years ago

Updated 11 months 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 13 hours ago

ThunderKittens by HazyResearch

CUDA kernel framework for fast deep learning primitives

karpathy:

jn2clark:

codekansas:

vincentweisser:

Created 2 years ago

Updated 3 weeks ago

hqq by dropbox

Model quantizer for fast, accurate post-training quantization, skipping calibration

zhyncs:

winglian:

hiyouga:

osanseviero:

Created 2 years ago

Updated 4 months ago

giskard-oss by Giskard-AI

Open-source testing framework for AI & LLM systems

tjbck:

shimmyshimmer:

chiphuyen:

zkolter:

Created 4 years ago

Updated 1 day ago

hackingBuddyGPT by ipa-lab

LLM agentic framework for security researchers/pen-testers

tjbck:

shimmyshimmer:

Created 2 years ago

Updated 3 months ago

open-webui by open-webui

Self-hosted AI platform for local LLM deployment

tobi:

karpathy:

wesm:

hammer:

Created 2 years ago

Updated 22 hours ago

marimo by marimo-team

AI-native reactive notebooks for reproducible Python development

tobi:

bcherny:

didierrlopes:

ekzhang:

Created 2 years ago

Updated 23 hours ago

dialog by talkdai

RAG LLM Ops app for simplified deployment and testing

tjbck:

shimmyshimmer:

Created 2 years ago

Updated 1 year ago

llmware by llmware-ai

Framework for enterprise RAG pipelines using small, specialized models

chiphuyen:

nirga:

tjbck:

shimmyshimmer:

Created 2 years ago

Updated 1 month ago

marqo by marqo-ai

End-to-end vector search engine for text and images

luiscape:

osanseviero:

shimmyshimmer:

chiphuyen:

Created 4 years ago

Updated 22 hours ago

llm.c by karpathy

LLM training in pure C/CUDA, no PyTorch needed

norvig:

alexey-milovidov:

didierrlopes:

hiyouga:

Created 2 years ago

Updated 1 year ago

cifar10-airbench by KellerJordan

Fast CIFAR-10 training benchmarks

abidlabs:

claforte:

Created 2 years ago

Updated 7 months ago

hlb-gpt by tysam-code

Researcher's toolbench for GPT model exploration

geohot:

winglian:

Created 3 years ago

Updated 1 year ago

SWE-agent by SWE-agent

Agent for automated software engineering (NeurIPS 2024)

truell20:

hugs:

chiphuyen:

ogabrielluiz:

Created 2 years ago

Updated 4 days ago

hackathon by mistralai-sf24

Minimal code for running and finetuning a 7B transformer model

winglian:

Created 2 years ago

Updated 2 years ago

OpenHands by OpenHands

AI platform for software development agents

truell20:

pgarbacki:

khou22:

yiranwu0:

Created 2 years ago

Updated 22 hours ago

fsdp_qlora by AnswerDotAI

Training script for LLMs using QLoRA + FSDP

hammer:

calvinfo:

chiphuyen:

mlabonne:

Created 2 years ago

Updated 1 year ago

GaLore by jiaweizzhao

Memory-efficient training for large language models via gradient low-rank projection

vincentweisser:

hiyouga:

Created 2 years ago

Updated 1 year ago

transformers by huggingface

ML library for pretrained model inference and training

clmnt:

lilianweng:

karpathy:

tjbck:

Created 7 years ago

Updated 13 hours ago

minbpe by karpathy

Minimal BPE encoder/decoder for LLM tokenization

hammer:

willingc:

chiphuyen:

shizhediao:

Created 2 years ago

Updated 2 years ago

jan by janhq

Local AI assistant for offline LLM use

tobi:

simonw:

joewalnes:

hammer:

Created 2 years ago

Updated 1 day ago

LlamaFactory by hiyouga

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

hiyouga:

patrickvonplaten:

alexchen4ai:

teetone:

Created 3 years ago

Updated 1 day ago

trl by huggingface

Library for transformer RL

jeffchuber:

vincentweisser:

tjbck:

alexchen4ai:

Created 6 years ago

Updated 13 hours ago

open_llama by openlm-research

Open-source reproduction of LLaMA models

chiphuyen:

shizhediao:

ebursztein:

zhuohan123:

Created 3 years ago

Updated 3 years ago

sentencepiece by google

Unsupervised text tokenizer for neural network generation

alexchen4ai:

gakonst:

transitive-bullshit:

peakji:

Created 9 years ago

Updated 1 week ago

cleanlab by cleanlab

Data-centric AI package for ML with messy data

chiphuyen:

alexanderatallah:

transitive-bullshit:

simonw:

Created 8 years ago

Updated 5 months ago

RAdam by LiyuanLucasLiu

Optimizer for neural network training, addressing adaptive learning rate variance

millionintegrals:

rwightman:

jwyang:

hiyouga:

Created 7 years ago

Updated 5 years ago

gpt-2 by openai

Code for research paper "Language Models are Unsupervised Multitask Learners"

aravindsrinivas:

simonw:

0hq:

shyamal-anadkat:

Created 7 years ago

Updated 1 year ago

streamlit by streamlit

SDK for rapidly building interactive data apps

kellyamanda:

treuille:

hsbt:

samuelcolvin:

Created 6 years ago

Updated 1 day ago

bert by google-research

TensorFlow code and pre-trained models for BERT

aravindsrinivas:

pgarbacki:

jn2clark:

evhub:

Created 7 years ago

Updated 1 year ago

nmslib by nmslib

Fast similarity search for non-metric spaces

transitive-bullshit:

parano:

ankane:

hammer:

Created 13 years ago

Updated 2 months ago

hnswlib by nmslib

Header-only C++ library for fast approximate nearest neighbors

lilianweng:

peakji:

kelvich:

0hq:

Created 9 years ago

Updated 3 months ago

ann-benchmarks by erikbern

ANN benchmarks for approximate nearest neighbor search algorithms

transitive-bullshit:

omarsar:

brendanfalk:

chiphuyen:

Created 11 years ago

Updated 1 day ago

faiss by facebookresearch

Similarity search library for dense vectors

lilianweng:

aravindsrinivas:

hsbt:

khou22:

Created 9 years ago

Updated 21 hours ago

ML-From-Scratch by eriklindernoren

ML model implementations from scratch, focused on accessibility

aravindsrinivas:

shadcn:

bcherny:

spartee:

Created 9 years ago

Updated 2 years ago

scattertext by JasonKessler

Tool for visualizing language differences across document types

hammer:

luiscape:

cvalenzuela:

Created 10 years ago

Updated 1 week ago

umap by lmcinnes

Dimension reduction technique for visualization and general non-linear reduction

transitive-bullshit:

lewtun:

ankane:

patrick-kidger:

Created 9 years ago

Updated 1 month ago

awesome-machine-learning by josephmisiti

Curated list of ML frameworks, libraries, and software

bcherny:

vincentweisser:

generall:

parano:

Created 12 years ago

Updated 3 weeks ago

tensorflow by tensorflow

Open-source ML framework

norvig:

aravindsrinivas:

karpathy:

bcherny:

Created 10 years ago

Updated 13 hours ago

examples by pytorch

PyTorch examples for diverse AI tasks

lilianweng:

hammer:

tjbck:

ari-holtzman:

Created 10 years ago

Updated 10 months ago

Feedback? Help us improve.