Zeyi-Lin

LLaMA-Factory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

SwanLab

⚡️SwanLab - an open-source, modern-design AI training tracking and visualization tool. Supports Cloud / Self-hosted use. Integrated with PyTorch / Transformers / LLaMA Factory / veRL/ Swift / Ultralytics / MMEngine / Keras etc.

SwanLab-Docs

SwanLab Official Documentation | SwanLab官方文档

HivisionIDPhotos

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

LLM-Finetune

大语言模型微调，Qwen2VL、Qwen2、GLM4指令微调

PaddleOCR-Online

Visualize the PaddleOCR2PyTorch project online to make the PaddleOCR experience and deployment easier.

Qwen2-VL-finetune-LatexOCR

Qwen3-Medical-SFT

Qwen3 Fine-tuning: Medical R1 Style Chat

Stable-Diffusion-Example

Stable Diffusion模型训练样例代码

Zeyi-Lin/HivisionIDPhotos

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

Zeyi-Lin/LLM-Finetune

大语言模型微调，Qwen2VL、Qwen2、GLM4指令微调

Zeyi-Lin/Qwen3-Medical-SFT

Qwen3 Fine-tuning: Medical R1 Style Chat

Zeyi-Lin/Qwen2-VL-finetune-LatexOCR

Zeyi-Lin/easy-r1

Train deepseek r1-like reasoning LLM with ease | 轻松训练1个deepseek r1类的推理LLM

Zeyi-Lin/UNet-Medical

Medical Image Segmentation Tutorial Case Studies - 医学影像分割教程案例

Zeyi-Lin/self-llm

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合**宝宝的部署教程

Zeyi-Lin/SwanBook-RL

强化学习实战教程：从QLearning, DQN, PPO 到 LLM RL

Zeyi-Lin/zeyi-lin

Zeyi-Lin/LLaMA-Factory

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)

Zeyi-Lin/ROLL

Zeyi-Lin/EasyR1

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

Zeyi-Lin/happy-llm

📚 从零开始的大语言模型原理与实践教程

Zeyi-Lin/lerobot

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

Zeyi-Lin/NexusGate

Zeyi-Lin/CSInternship2025

Zeyi-Lin/DiffSynth-Studio

Enjoy the magic of Diffusion models!

Zeyi-Lin/diffusion-lora-dog

Zeyi-Lin/evalscope

A streamlined and customizable framework for efficient large model evaluation and performance benchmarking

Zeyi-Lin/LLaMA-Factory-Doc

LLaMA Factory Document

Zeyi-Lin/MiniCPM-Lora

Zeyi-Lin/mmengine

OpenMMLab Foundational Library for Training Deep Learning Models

Zeyi-Lin/MNIST-examples

MNIST、FashionMNIST、Cifar10 PyTorch Training Code

Zeyi-Lin/ms-swift

Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, InternVL2.5, MiniCPM-V-2.6, GLM4v, Xcomposer2.5, Yi-VL, DeepSeek-VL2, Phi3.5-Vision, GOT-OCR2, ...).

Zeyi-Lin/OpenRLHF

An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & RingAttention & RFT)

Zeyi-Lin/PaddleNLP

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

Zeyi-Lin/Qwen3-SmVL

将SmolVLM2的视觉头与Qwen3-0.6B模型进行了拼接微调

Zeyi-Lin/transformers

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Zeyi-Lin/ultralytics

Ultralytics YOLO11 🚀

Zeyi-Lin/verl

verl: Volcano Engine Reinforcement Learning for LLMs