SII-OpenMOSS

SII-OpenMOSS's repositories

An open-source tool-augmented conversational language model from Fudan University

Language:PythonApache-2.012058 121 355

Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"

Language:Python862 21 45

Collaborative Training of Large Language Models in an Efficient Way

Language:PythonApache-2.0415 11 69

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

Language:PythonApache-2.0311 6 5

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

Language:PythonMIT286 4 6

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

Language:PythonApache-2.0124 50

For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.

Language:Python107 5 21

[ICML'2024] Can AI Assistants Know What They Don't Know?

Language:Python7906

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

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

Language:PythonApache-2.055 2 1

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

Language:PythonMIT2 10

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

100

A library for mechanistic interpretability of GPT-style language models

Language:PythonMIT000