BGE-M3 is a new model from BAAI distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.
EXAONE 3.5 is a collection of instruction-tuned bilingual (English and Korean) generative models ranging from 2.4B to 32B parameters, developed and released by LG AI Research.
BGE-Reranker-v2-M3 是轻量级重排序模型，基于 BGE-M3-0.5B 架构优化，专为多语言检索任务设计，尤其强化了中英文混合场景下的性能。其核心定位是为RAG流程提供高效的上下文重排序能力。
BGE-M3文本向量模型在继承BGE模型优点的基础上，实现了多项技术突破。BGE-M3支持超过100种语言的语义表示及检索任务，具备领先的多语言、跨语言检索能力。支持8192长度。
The IBM Granite Embedding 30M and 278M models models are text-only dense biencoder embedding models, with 30M available in English only and 278M serving multilingual use cases.
quantize https://huggingface.co/BAAI/bge-m3 to f16 / q8_0 (latest) / q4_k_m
Multi-Lingual, Multi-Functionality, Multi-Granularity bge-m3-korean from upskyy
It is BAAI/bge-m3
chatfire模型仓库