Hong-Jia Chen

unsloth. Unsloth is a local UI for training and running Kimi K3, Gemma 4, Qwen3.6, DeepSeek-V4, GLM and other models.

open-r1. Fully open reproduction of DeepSeek-R1

LLM101n. LLM101n: Let's build a Storyteller

top-cvpr-2024-papers. This repository is a curated collection of the most exciting and influential CVPR 2024 papers. 🔥 [Paper + Code + Demo]

build-nanogpt. Video+code lecture on building nanoGPT from scratch

llama3-from-scratch. llama3 implementation one matrix multiplication at a time

LLaVA-pp. 🔥🔥 LLaVA++: Extending LLaVA with Phi-3 and LLaMA-3 (LLaVA LLaMA-3, LLaVA Phi-3)

torchtitan. A PyTorch native platform for training generative AI models

schedule_free. Schedule-Free Optimization in PyTorch

dadaptation. D-Adaptation for SGD, Adam and AdaGrad

python-mastery. Advanced Python Mastery (course by @dabeaz)

copilot-analysis. 本文详细分析了 Github Copilot 这个基于机器学习的代码自动补全工具的实现原理。作者通过逆向工程的方式,深入探索了 Copilot 的核心逻辑,包括代码提示的入口、获取提示的核心方法、以及相关的缓存策略、实验特性等。

open_clip. An open source implementation of CLIP.

DragGAN. Official Code for DragGAN (SIGGRAPH 2023)

HPM. [CVPR'23 & TPAMI'25] Hard Patches Mining for Masked Image Modeling & Bootstrap Masked Visual Modeling via Hard Patch Mining

Segment-Everything-Everywhere-All-At-Once. [NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

AnimatedDrawings. Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

Grounded-Segment-Anything. Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Semantic-Segment-Anything. Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

Kaggle-Ensemble-Guide. Code for the Kaggle Ensembling Guide Article on MLWave

babyagi. Python

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.

the-algorithm-ml. Source code for Twitter's Recommendation Algorithm

the-algorithm. Source code for the X Recommendation Algorithm

HowToLiveLonger. 程序员延寿指南 | A programmer's guide to live longer

whisper-subtitles. Apple PodCast Transcription with OpenAI's Whisper

N46Whisper. Whisper based Japanese subtitle generator

ml-ane-transformers. Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)

chatgpt-retrieval-plugin. The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

evals. Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

TaskMatrix. Python

dgl. Python package built to ease deep learning on graph, on top of existing DL frameworks.

prismer. The implementation of "Prismer: A Vision-Language Model with Multi-Task Experts".

CutLER. Code release for "Cut and Learn for Unsupervised Object Detection and Instance Segmentation" and "VideoCutLER: Surprisingly Simple Unsupervised Video Instance Segmentation"

composer. Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"

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

hlb-CIFAR10. Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)

tuning_playbook_zh-CN. A playbook for systematically maximizing the performance of deep learning models.

Attention-driven-Masking-and-Throwing. Python

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

ConvNeXt-V2. Code release for ConvNeXt V2 model

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

HelloGitHub. :octocat: 分享 GitHub 上有趣、入门级的开源项目。Share interesting, entry-level open source projects on GitHub.

awesome-self-supervised-learning. A curated list of awesome self-supervised methods

Auto-Photoshop-StableDiffusion-Plugin. A user-friendly plug-in that makes it easy to generate stable diffusion images inside Photoshop using either Automatic or ComfyUI as a backend.

best_AI_papers_2022. A curated list of the latest breakthroughs in AI (in 2022) by release date with a clear video explanation, link to a more in-depth article, and code.

PaLM-rlhf-pytorch. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

EfficientFormer. EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

cornell-cs5785-2020-applied-ml. Teaching materials for the applied machine learning course at Cornell Tech (online edition)

TextRL. Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-176B/bloom/gpt/bart/T5/MetaICL)

Awesome-Masked-Autoencoders. A collection of literature after or concurrent with Masked Autoencoder (MAE) (Kaiming He el al.).

gpt-ai-assistant. OpenAI + LINE + Vercel = GPT AI Assistant

SimCLRv2-Pytorch. Pretrained SimCLRv2 models in Pytorch

pytorch_forward_forward. Implementation of Hinton's forward-forward (FF) algorithm - an alternative to back-propagation

Transformers-Tutorials. This repository contains demos I made with the Transformers library by HuggingFace.

FasterTransformer. Transformer related optimization, including BERT, GPT

chatgpt-mac. ChatGPT for Mac, living in your menubar.

awesome-federated-learning. All materials you need for Federated Learning: blogs, videos, papers, and softwares, etc.

FedMatch. This repository is an official Tensorflow 2 implementation of Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning

transferlearning. Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

TorchSSL. A PyTorch-based library for semi-supervised learning (NeurIPS'21)

awesome-semi-supervised-learning. 😎 An up-to-date & curated list of awesome semi-supervised learning papers, methods & resources.

lightweight-neural-architecture-search. This is a collection of our zero-cost NAS and efficient vision applications.

Versatile-Diffusion. Versatile Diffusion: Text, Images and Variations All in One Diffusion Model, arXiv 2022 / ICCV 2023

learned_optimization. Python

SEAL. Microsoft SEAL is an easy-to-use and powerful homomorphic encryption library.

Pyfhel. PYthon For Homomorphic Encryption Libraries, perform encrypted computations such as sum, mult, scalar product or matrix multiplication in Python, with NumPy compatibility. Uses SEAL/PALISADE as backends, implemented using Cython.

galai. Model API for GALACTICA

FidelityFX-FSR2. FidelityFX Super Resolution 2

PaddleSlim. PaddleSlim is an open-source library for deep model compression and architecture search.

ECCV2026-Papers-with-Code. ECCV 2026 论文和开源项目合集，同时欢迎各位大佬提交issue，分享ECCV 2026论文和开源项目

MPL-pytorch. Unofficial PyTorch implementation of "Meta Pseudo Labels"

model-soups. Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

harmonia. Federated Learning Made Easy

AITemplate. AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

makemore. An autoregressive character-level language model for making more things

git-re-basin-pytorch. Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch

Federated-Learning. 联邦学习

GFL. Galaxy Federated Learning Framework （星际联邦学习框架）

FixMatch-pytorch. Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"

mypy. Optional static typing for Python

pytorchTutorial. PyTorch Tutorials from my YouTube channel

Paddle. PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice （『飞桨』核心框架，深度学习&机器学习高性能单机、分布式训练和跨平台部署）

SPD-Conv. Code for ECML PKDD 2022 paper: No More Strided Convolutions or Pooling: A Novel CNN Architecture for Low-Resolution Images and Small Objects

pandas. Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

stable-diffusion. A latent text-to-image diffusion model

Python-Head-First-Design-Patterns. Python for Head First Design Patterns book (2020)

wails. Create beautiful applications using Go

affine-client. client for https://github.com/toeverything/AFFiNE

AFFiNE. There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use.

Next-ViT. Python

ml-mobileone. This repository contains the official implementation of the research paper, "An Improved One millisecond Mobile Backbone" CVPR 2023.

professional-programming. A collection of learning resources for curious software engineers

SLaK. [ICLR 2023] "More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity"; [ICML 2023] "Are Large Kernels Better Teachers than Transformers for ConvNets?"

GPU-Puzzles. Solve puzzles. Learn CUDA.

yolov7. Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

BoT-SORT. BoT-SORT: Robust Associations Multi-Pedestrian Tracking

awesome-mac.  This project is dedicated to collecting high-quality macOS software and organizing them systematically by different categories for easy search and use.

discoart. 🪩 Create Disco Diffusion artworks in one line

Software-Engineering-at-Google. 《Software Engineering at Google》的中英文对译版本