BGE-Base-en

Name: BAAI General Embedding - Base - en
Author: 北京智源人工智能研究院

embedding模型

BAAI General Embedding - Base - en

Release date: 2023-08-02更新于: 2023-08-08 16:26:21.778583

Live demo

BAAI General Embedding - Base - en is an AI model published by 北京智源人工智能研究院, released on 2023-08-02, for embedding模型, with 0.0B parameters, and 512 tokens context length, requiring about 438MB storage, under the MIT License license.

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

BGE-Base-en

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

2023-08-02

Model file size

438MB

MoE architecture

Total params / Active params

No data / N/A

Knowledge cutoff

No data

BGE-Base-en

Open source & experience

Code license

MIT License

Weights license

MIT License- 免费商用授权

GitHub repo

https://github.com/FlagOpen/FlagEmbedding

Hugging Face

https://huggingface.co/BAAI/bge-base-en

Live demo

No live demo

BAAI General Embedding - Base - en

Model Overview

BAAI General Embedding是北京智源人工智能研究院开源的一系列embedding大模型，支持中文和英文的embedding。效果很好，重要的是免费商用授权！

BAAI General Embedding - base - en是其中的英文版本，是一个中等规模参数的版本。不过官方并未透露其参数大小。该模型的维度是1024，最高支持输入的序列长度是512。在MTEB评分中超过了OpenAI的text-embedding-ada-002，但是比bge-large-en效果稍差（ https://www.datalearner.com/ai-models/pretrained-models/bge-large-en ）。

BGE-Base-en

Model basics

Open source & experience

Official resources

API details

Benchmark Results

Publisher

Model Overview

DataLearner 官方微信