Building a inclusive, scalable, and high-performance multilingual translation model

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

slime is an LLM post-training framework for RL Scaling.

Wan: Open and Advanced Large-Scale Video Generative Models

FlashMLA: Efficient Multi-head Latent Attention Kernels

MoBA: Mixture of Block Attention for Long-Context LLMs

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Curated list of datasets and tools for post-training.

Democratizing Reinforcement Learning for LLMs

Simple RL training for reasoning

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

🍼 Official implementation of Dynamic Data Mixing Maximizes Instruction Tuning for Mixture-of-Experts

Code for BLT research paper

Machine Learning Engineering Open Book

Cool Papers - Immersive Paper Discovery

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

🧑‍🚀 全世界最好的LLM资料总结（多模态生成、Agent、辅助编程、AI审稿、数据处理、模型训练、模型推理、o1 模型、MCP、小语言模型、视觉语言模型） | Summary of the world's best LLM resources.

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

Next-Token Prediction is All You Need

O1 Replication Journey

This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-vision models.

A repository sharing the literatures about long-context large language models, including the methodologies and the evaluation benchmarks

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

A generative speech model for daily dialogue.

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型