OpenMOSS (SII)
OpenMOSS presents our LLM research, supported by SII and Fudan, led by Professor Xipeng Qiu.
China
Pinned Repositories
AnyGPT
Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"
CoLLiE
Collaborative Training of Large Language Models in an Efficient Way
GAOKAO-MM
[ACL'2024 Findings] GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models Evaluation
HalluQA
Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"
Language-Model-SAEs
Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.
MOSS
An open-source tool-augmented conversational language model from Fudan University
MOSS-TTSD
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.
Say-I-Dont-Know
[ICML'2024] Can AI Assistants Know What They Don't Know?
SpeechGPT-2.0-preview
GPT-4o-level, real-time spoken dialogue system.
VLABench
Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.
OpenMOSS (SII)'s Repositories
OpenMOSS/MOSS
An open-source tool-augmented conversational language model from Fudan University
OpenMOSS/MOSS-TTSD
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.
OpenMOSS/AnyGPT
Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"
OpenMOSS/CoLLiE
Collaborative Training of Large Language Models in an Efficient Way
OpenMOSS/SpeechGPT-2.0-preview
GPT-4o-level, real-time spoken dialogue system.
OpenMOSS/VLABench
Official repo of VLABench, a large scale benchmark designed for fairly evaluating VLA, Embodied Agent, and VLMs.
OpenMOSS/Language-Model-SAEs
Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.
OpenMOSS/HalluQA
Dataset and evaluation script for "Evaluating Hallucinations in Chinese Large Language Models"
OpenMOSS/Say-I-Dont-Know
[ICML'2024] Can AI Assistants Know What They Don't Know?
OpenMOSS/GAOKAO-MM
[ACL'2024 Findings] GAOKAO-MM: A Chinese Human-Level Benchmark for Multimodal Models Evaluation
OpenMOSS/Thus-Spake-Long-Context-LLM
a survey of long-context LLMs from four perspectives, architecture, infrastructure, training, and evaluation
OpenMOSS/LongLLaDA
LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs
OpenMOSS/Lorsa
OpenMOSS/Embodied-Planner-R1
Embodied-Planner-R1: Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning
OpenMOSS/FDU-PRML-2025Fall
复旦大学《模式识别与机器学习》课程仓库
OpenMOSS/VehicleWorld
VehicleWorld is the first comprehensive multi-device environment for intelligent vehicle interaction that accurately models the complex, interconnected systems in modern cockpits.
OpenMOSS/UnifiedToolHub
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.
OpenMOSS/ReAttention
[ICLR2025] ReAttention, a training-free approach to break the maximum context length in length extrapolation
OpenMOSS/LongSafety
OpenMOSS/FDU-AI-PRML-2024Fall
OpenMOSS/MOSS-VoicePlus
OpenMOSS/TransformerLens
A library for mechanistic interpretability of GPT-style language models
OpenMOSS/Ultra-Innerthought
Ultra-Innerthought is a bilingual (Chinese and English) open-domain R1/o1 style SFT dataset.
OpenMOSS/sglang
OpenMOSS/.github
OpenMOSS/OpenMOSS.github.io
Website for the OpenMOSS