A suite of multimodal language models that are powerful and efficient

Reproducible Language Agent Research

Build multimodal language agents for fast prototype and production

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

A Comprehensive Evaluation Benchmark for Open-Vocabulary Detection (AAAI 2024)

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。