"LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"

Fully Open Framework for Democratized Multimodal Training

Flexible and Pluggable Serving Engine for Diffusion LLMs

a toolkit on knowledge distillation for large language models

Fully open reproduction of DeepSeek-R1

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

Scalable RL solution for advanced reasoning of language models

A high-throughput and memory-efficient inference and serving engine for LLMs

A Gemini 2.5 Flash Level MLLM for Vision, Speech, and Full-Duplex Multimodal Live Streaming on Your Phone

An open-source implementation for training LLaVA-NeXT.

[ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

Generative Models by Stability AI

The plan which extend ChatHaruhi into Zero-shot Roleplaying model

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

[NeurIPS 2022] Official Code for "Benchmarking 3D Pose and Shape Estimation Beyond Algorithms"

OpenMMLab Model Compression Toolbox and Benchmark.

OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image genera…

[ECCV 2022] Official implementation of the paper "SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos"

The official code for BSTRO in paper: Capturing and Inferring Dense Full-Body Human-Scene Contact, CVPR2022

OpenMMLab Text Detection, Recognition and Understanding Toolbox

A memory balanced and communication efficient FullyConnected layer with CrossEntropyLoss model parallel implementation in PyTorch

C++ Parallel Computing and Asynchronous Networking Framework

SPOS(Single Path One-Shot Neural Architecture Search with Uniform Sampling) rebuilt in Pytorch with single GPU.

Fast and Accurate ML in 3 Lines of Code

[ICCV 2019, Oral] Controllable Artistic Text Style Transfer via Shape-Matching GAN

Single Path One-Shot NAS MXNet implementation with full training and searching pipeline. Support both Block and Channel Selection. Searched models better than the original paper are provided.

TorchCV: A PyTorch-Based Framework for Deep Learning in Computer Vision