m3e-Large

Name: Moka Massive Mixed Embedding-Large
Author: Moka-AI

embedding模型

Moka Massive Mixed Embedding-Large

Release date: 2023-06-07更新于: 2023-08-08 17:29:44.455379

Live demo

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

m3e-Large

Model basics

Reasoning traces

Not supported

Thinking modes

Thinking modes not supported

Context length

512 tokens

Max output length

No data

Model type

embedding模型

Release date

2023-06-07

Model file size

1.3

MoE architecture

Total params / Active params

3.4B / N/A

Knowledge cutoff

No data

m3e-Large

Open source & experience

Code license

开源不可商用

Weights license

开源不可商用- 不可以商用

GitHub repo

https://github.com/Moka-AI

Hugging Face

https://huggingface.co/moka-ai/m3e-large

Live demo

No live demo

Moka Massive Mixed Embedding-Large

Model Overview

M3E 是 Moka Massive Mixed Embedding 的缩写

Moka，此模型由 MokaAI 训练，开源和评测，训练脚本使用 uniem ，评测 BenchMark 使用 MTEB-zh
Massive，此模型通过千万级 (2200w+) 的中文句对数据集进行训练
Mixed，此模型支持中英双语的同质文本相似度计算，异质文本检索等功能，未来还会支持代码检索
Embedding，此模型是文本嵌入模型，可以将自然语言转换成稠密的向量

DataLearner 官方微信

欢迎关注 DataLearner 官方微信，获得最新 AI 技术推送

m3e-Large

Model basics

Open source & experience

Official resources

API details

Benchmark Results

Publisher

Model Overview

DataLearner 官方微信