Repositories list

• rope_pp

  Public
  Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs

  Python

  •1•11•0•0•Updated Dec 9, 2025Dec 9, 2025

• Language-Model-SAEs

  Public

  OpenMOSS/Language-Model-SAEs’s past year of commit activity
  Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.

  sparse-autoencodersinterpretabilitysparse-dictionary+ 1mechanistic-interpretability

  Python

  •21•168•11•0•Updated Dec 8, 2025Dec 8, 2025

• MOSS-TTSD

  Public
  MOSS-TTSD is a spoken dialogue generation model that enables expressive dialogue speech synthesis in both Chinese and English, supporting zero-shot multi-speaker voice cloning, and long-form speech generation.

  streamingfinetunetext-to-speeh+ 3large-language-modelssglangspeech-dialogue-generation

  Python

  •

  Apache License 2.0

  •94•1.1k•46•0•Updated Dec 8, 2025Dec 8, 2025

• LongLLaDA

  Public
  LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs

  diffusionlarge-language-modelslong-context+ 2length-extrapolationdiffusion-language-models

  Python

  •5•46•2•0•Updated Dec 7, 2025Dec 7, 2025

• DiRL

  Public

  OpenMOSS/DiRL’s past year of commit activity
  Python

  •

  Apache License 2.0

  •2•91•0•0•Updated Dec 7, 2025Dec 7, 2025

• MOSS-Speech

  Public
  MOSS-Speech is a true speech-to-speech large language model without text guidance.

  voice-assistantspeech-to-speechlarge-language-models

  Python

  •

  Apache License 2.0

  •5•107•2•0•Updated Dec 4, 2025Dec 4, 2025

• TransformerLens

  Public
  A library for mechanistic interpretability of GPT-style language models

  Python

  •

  MIT License

  •479•2•0•0•Updated Dec 3, 2025Dec 3, 2025

• FDU-PRML-2025Fall

  Public

  OpenMOSS/FDU-PRML-2025Fall’s past year of commit activity
  复旦大学《模式识别与机器学习》课程仓库

  Python

  •17•33•0•0•Updated Nov 27, 2025Nov 27, 2025

• OpenMOSS.github.io

  Public
  JavaScript

  •2•1•0•0•Updated Nov 25, 2025Nov 25, 2025

• .github

  Public

  OpenMOSS/.github’s past year of commit activity
  0•0•0•0•Updated Nov 24, 2025Nov 24, 2025

• RoboOmni

  Public
  Official code of "RoboOmni: Proactive Robot Manipulation in Omni-modal Context"

  Python

  •4•74•1•0•Updated Nov 17, 2025Nov 17, 2025

• sglang

  Public
  Python

  •

  Apache License 2.0

  •0•1•1•0•Updated Nov 14, 2025Nov 14, 2025

• VLABench

  Public
  Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.

  roboticsembodiedfoundation-models

  Python

  •

  MIT License

  •20•339•24•0•Updated Nov 11, 2025Nov 11, 2025

• Lorsa

  Public
  Python

  •0•29•0•0•Updated Nov 9, 2025Nov 9, 2025

• Website

  Public
  wangye

  JavaScript

  •2•0•0•1•Updated Nov 7, 2025Nov 7, 2025

• Sparse-dLLM

  Public
  Python

  •2•16•1•0•Updated Oct 16, 2025Oct 16, 2025

• ReAttention

  Public
  [ICLR2025] ReAttention, a training-free approach to break the maximum context length in length extrapolation

  tritonlong-contextlarge-language-model+ 1length-extrapolation

  Python

  •

  MIT License

  •0•14•0•0•Updated Oct 6, 2025Oct 6, 2025

• Embodied-Planner-R1

  Public
  Embodied-Planner-R1: Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning

  Python

  •

  Apache License 2.0

  •1•20•0•3•Updated Sep 22, 2025Sep 22, 2025

• VehicleWorld

  Public
  VehicleWorld is the first comprehensive multi-device environment for intelligent vehicle interaction that accurately models the complex, interconnected systems in modern cockpits.

  Python

  •0•20•0•0•Updated Sep 16, 2025Sep 16, 2025

• UnifiedToolHub

  Public
  UnifiedToolHub is a comprehensive project supporting LLM-based tool use, designed to unify various tool-use dataset formats and provide training preparation, annotation, and evaluation functionalities.

  tool-usellmfunction-calling

  Python

  •4•15•0•0•Updated Jul 23, 2025Jul 23, 2025

• LongSafety

  Public
  Python

  •0•8•2•0•Updated Jun 16, 2025Jun 16, 2025

• Thus-Spake-Long-Context-LLM

  Public
  a survey of long-context LLMs from four perspectives, architecture, infrastructure, training, and evaluation

  traininginfrastructurearchitecture+ 5evaluationsurveypaper-listlong-contextlarge-language-model

  1•60•1•0•Updated Mar 31, 2025Mar 31, 2025

• Ultra-Innerthought

  Public
  Ultra-Innerthought is a bilingual (Chinese and English) open-domain R1/o1 style SFT dataset.

  reasoningsynthetic-datalarge-language-models

  0•3•0•0•Updated Feb 14, 2025Feb 14, 2025

• SpeechGPT-2.0-preview

  Public
  GPT-4o-level, real-time spoken dialogue system.

  Python

  •

  Apache License 2.0

  •29•362•7•0•Updated Jan 27, 2025Jan 27, 2025

• FDU-AI-PRML-2024Fall

  Public
  Python

  •3•6•1•0•Updated Nov 28, 2024Nov 28, 2024

• CoLLiE

  Public

  OpenMOSS/CoLLiE’s past year of commit activity
  Collaborative Training of Large Language Models in an Efficient Way

  nlpdeep-learningpytorch+ 1deepspeed

  Python

  •

  Apache License 2.0

  •58•417•20•5•Updated Aug 28, 2024Aug 28, 2024

• AnyGPT

  Public

  OpenMOSS/AnyGPT’s past year of commit activity
  Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

  Python

  •71•862•18•3•Updated Aug 27, 2024Aug 27, 2024

• MOSS

  Public

  OpenMOSS/MOSS’s past year of commit activity
  An open-source tool-augmented conversational language model from Fudan University

  natural-language-processingdeep-learningtext-generation+ 3dialogue-systemslarge-language-modelschatgpt

  Python

  •

  Apache License 2.0

  •1.1k•12k•235•6•Updated Jul 13, 2024Jul 13, 2024

• HalluQA

  Public
  Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"

  question-answeringhallucinationslarge-language-models

  Python

  •

  Apache License 2.0

  •6•136•0•0•Updated Jun 5, 2024Jun 5, 2024

• GAOKAO-MM

  Public
  [ACL'2024 Findings] GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models Evaluation

  Python

  •

  Apache License 2.0

  •6•73•1•0•Updated Mar 13, 2024Mar 13, 2024