Skip to content
InternLM

GitHub Org's stars

Welcome to the InternLM organization. InternLM is mainly developed by Shanghai AI Laboratory. We keep open-sourcing high quality LLMs as well as a full-stack toolchain for development and application.

Models

  • Intern-S1: a multimodal reasoning model with strong general capabilities and state-of-the-art performance on a wide range of scientific tasks.
  • InternLM: a series of multi-lingual foundation models and chat models.
  • InternLM-Math: state-of-the-art bilingual math reasoning LLMs.
  • InternLM-XComposer: a vision-language large model (VLLM) based on InternLM for advanced text-image comprehension and composition.

Toolchain

  • InternEvo: a lightweight framework for large-scale model pre-training and finetuning.
  • XTuner: a toolkit for efficiently fine-tuning LLMs, supporting various models and fintuning algorithms.
  • LMDeploy: a toolkit for compressing, deploying, and serving LLMs.
  • Lagent: a lightweight framework that allows users to efficiently build LLM-based agents.
  • AgentLego: a library of versatile tool APIs to extend and enhance LLM-based agents, compatible with Lagent, Langchain, etc.
  • OpenCompass: a platform for large model evaluation, providing a fair, open, and reproducible benchmark.
  • OpenAOE: an elegant and out-of-the-box chat UI for comparing mulitple models.

Applications

  • HuixiangDou: a domain-specific assistant based on LLMs which can deal with complex techinical questions in group chats.
  • MindSearch: an LLM-based multi-agent framework of web search engine.

Pinned Loading

  1. InternLM InternLM Public

    Official release of InternLM series (InternLM, InternLM2, InternLM2.5, InternLM3).

    Python 7k 496

  2. lmdeploy lmdeploy Public

    LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

    Python 7k 599

  3. InternLM-XComposer InternLM-XComposer Public

    InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

    Python 2.9k 177

  4. xtuner xtuner Public

    A Next-Generation Training Engine Built for Ultra-Large MoE Models

    Python 4.8k 358

  5. MindSearch MindSearch Public

    🔍 An LLM-based Multi-agent Framework of Web Search Engine (like Perplexity.ai Pro and SearchGPT)

    JavaScript 6.6k 664

  6. InternLM-Math InternLM-Math Public

    State-of-the-art bilingual open-sourced Math reasoning LLMs.

    Python 519 34

Repositories

Showing 10 of 33 repositories
  • xtuner Public

    A Next-Generation Training Engine Built for Ultra-Large MoE Models

    InternLM/xtuner’s past year of commit activity
    Python 4,750 Apache-2.0 358 223 (2 issues need help) 30 Updated Sep 8, 2025
  • ClusterX Public
    InternLM/ClusterX’s past year of commit activity
    Python 4 0 0 0 Updated Sep 8, 2025
  • AdaptiveGEMM Public Forked from deepseek-ai/DeepGEMM

    AdaptiveGEMM: FP8 GEMM with Adaptation to Various Lengths of Group M

    InternLM/AdaptiveGEMM’s past year of commit activity
    Cuda 2 MIT 696 0 0 Updated Sep 8, 2025
  • GroupedGEMM Public Forked from fanshiqing/grouped_gemm

    PyTorch bindings for CUTLASS and CUBLAS Grouped GEMM, Permute and Unpermute.

    InternLM/GroupedGEMM’s past year of commit activity
    Cuda 2 Apache-2.0 75 0 0 Updated Sep 8, 2025
  • lmdeploy Public

    LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

    InternLM/lmdeploy’s past year of commit activity
    Python 6,985 Apache-2.0 599 481 34 Updated Sep 8, 2025
  • Intern-S1 Public

    A Scientific Multimodal Foundation Model

    InternLM/Intern-S1’s past year of commit activity
    560 Apache-2.0 25 12 0 Updated Sep 2, 2025
  • InternLM/InternBootcamp’s past year of commit activity
    Python 227 Apache-2.0 23 0 0 Updated Aug 29, 2025
  • InternEvo Public

    InternEvo is an open-sourced lightweight training framework aims to support model pre-training without the need for extensive dependencies.

    InternLM/InternEvo’s past year of commit activity
    Python 406 Apache-2.0 69 49 21 Updated Aug 21, 2025
  • HuixiangDou Public

    HuixiangDou: Overcoming Group Chat Scenarios with LLM-based Technical Assistance

    InternLM/HuixiangDou’s past year of commit activity
    Python 2,428 BSD-3-Clause 180 32 3 Updated Aug 13, 2025
  • lagent Public

    A lightweight framework for building LLM-based agents

    InternLM/lagent’s past year of commit activity
    Python 2,189 Apache-2.0 223 5 10 Updated Aug 6, 2025