Projects sharing features with MiMo

Qwen2.5 is a suite of large language model foundation models designed for natural language generation, code production, and complex mathematical reasoning. The project encompasses a multilingual language model capable of processing dozens of languages and a specialized code generation model for technical problem solving and debugging. The framework is distinguished by its long context capabilities, enabling the analysis of massive inputs ranging from 256K up to 1 million tokens. It further functions as an agentic framework, utilizing standardized templates and parsers to execute autonomous wo

An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Skywork-R1V4

Megatron-LM is a distributed transformer training library and large language model training framework designed to scale models across thousands of GPUs. It functions as a GPU-optimized deep learning toolkit and a scaling engine for mixture-of-experts architectures, enabling the training of models with hundreds of billions of parameters. The project implements multi-dimensional model parallelism, combining tensor, pipeline, data, expert, and context-based workload distribution. It specifically optimizes mixture-of-experts architectures through integrated memory and communication improvements t

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.

GLM-4.5 is a multimodal large language model and advanced reasoning system. It functions as an AI coding assistant, an autonomous AI agent, and a multimodal content generator capable of processing and generating text, images, audio, and video within a single unified system. The project is distinguished by its deep reasoning capabilities, utilizing chain-of-thought processing to solve complex mathematical, logical, and technical problems. It features an agentic architecture that allows for autonomous task execution, long-horizon goal planning, and the ability to interact with external tools an

✊ Unleashing the Power of Reinforcement Learning for Math and Code Reasoners 🤖

From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓

This project is a quantized fine-tuning framework for large language models. It implements a low-rank adaptation library and a four-bit quantizer to reduce the GPU memory requirements needed to train large models. The framework utilizes four-bit quantization and low-rank adapters to enable model training on consumer-grade hardware. It further reduces the memory footprint through double quantization and a paged optimizer that offloads states to system RAM. The system supports distributed training across multiple GPUs to handle larger parameter scales and includes utilities for custom dataset

Reinforcement Learning Tuning for VideoLLMs: Reward Design and Data Efficiency

AudioGPT is an LLM-driven audio framework and processing suite that uses large language models to orchestrate neural audio pipelines. It functions as a multimodal audio generator and processing system, integrating a collection of pretrained models to handle speech synthesis, sound generation, and audio manipulation. The system is distinguished by its ability to generate audio from diverse inputs, including text and images, and its capacity to produce synchronized talking head videos. It also operates as a neural speech translator, converting spoken language between different tongues while pre

alpaca.cpp is a high-performance local inference engine implemented in C++ for executing instruction-tuned large language models. It serves as a quantized model runtime designed to load and run model tensors on local hardware with minimal dependencies, removing the requirement for a full Python environment. The project focuses on on-device text generation and the deployment of private AI chatbots. It utilizes model weight quantization to reduce memory requirements and increase inference speed on consumer-grade devices. The system covers hardware-optimized model execution through thread-pool

Petals is a decentralized framework and inference engine for running large language models across a peer-to-peer network. It enables the execution of models that exceed the memory of any single machine by splitting computations and model layers across a collaborative swarm of GPUs. The system functions as a collaborative compute network where participants share local GPU resources and host model weights. It supports distributed prompt-tuning to adapt massive models to specific tasks and allows for the establishment of private compute swarms to process sensitive data within restricted, trusted

Exploring Applications of GRPO

👋 Hi, everyone! We are ByteDance Seed Team.

Chroma is a specialized vector database designed to index and retrieve high-dimensional data representations for semantic similarity search. It functions as a comprehensive platform for information retrieval, enabling the storage and management of unstructured documents alongside structured metadata. By mapping data into numerical representations, the system facilitates rapid similarity lookups across large datasets. The platform distinguishes itself through a hybrid search infrastructure that combines dense vector embeddings with sparse keyword and regular expression matching to balance sema

Please refer to our new GitHub Wiki which documents our efforts in detail in creating the open source version of GitHub Copilot

Deepeval is a framework for testing and evaluating large language model applications. It provides a suite of tools for executing automated regression tests, validating model output quality against defined standards, and tracing the execution of complex agent workflows. By integrating these capabilities into development pipelines, the platform ensures consistent performance and reliability throughout the software lifecycle. The platform distinguishes itself through its focus on programmatic validation and observability. It utilizes secondary language models to score output quality and employs

ChatBot Injection and Exploit Examples: A Curated List of Prompt Engineer Commands - ChatGPT

StarCoder2 is a family of code generation models (3B, 7B, and 15B), trained on 600+ programming languages from The Stack v2 and some natural language text such as Wikipedia, Arxiv, and GitHub issues. The models use Grouped Query Attention, a context window of 16,384 tokens, with sliding window…