🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch and FLAX.

手把手带你实战 Huggingface Transformers 课程视频同步更新在B站与YouTube

The code and data of We-Math, accepted by ACL 2025 main conference.

Enjoy the magic of Diffusion models!

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

Official Implementation of Rectified Flow (ICLR2023 Spotlight)

STAT 453: Intro to Deep Learning @ UW-Madison (Spring 2021)

”数学不难“ 之 《线性代数不难》上下册，66话题完册；欢迎批评指正

Book_4_《矩阵力量》 | 鸢尾花书：从加减乘除到机器学习；上架！

Official code for "Top-Down Visual Attention from Analysis by Synthesis" (CVPR 2023 highlight)

从零手搓Flow Matching（Rectified Flow）

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

Unofficial implementation of Titans, SOTA memory for transformers, in Pytorch

Attention is all you need implementation

[ECCV 2022]Code for paper "DaViT: Dual Attention Vision Transformer"

Accelerator on how to finetune Microsoft's Florance-2 model for a variety of computer vision use cases.

Quick exploration into fine tuning florence 2

Florence-2

Taming Transformers for High-Resolution Image Synthesis

Next-Token Prediction is All You Need

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。

🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!

🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!

Official Repository of "Learning to Reason under Off-Policy Guidance"

✨✨Latest Advances on Multimodal Large Language Models

https://transformer-circuits.pub/2025/attribution-graphs/methods.html

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.