mxbai-embed-large - Ollama 框架

mxbai-embed-large

mixedbread.ai 最先進的大型嵌入模型

embedding 335m

1.2M 下載次數更新於 9 個月前

更新於 9 個月前

9 個月前

468836162de7 · 670MB

quantizationF16

{ "num_ctx": 512 }

Apache License Version 2.0, January 2004

說明文件

mxbai-embed-large

截至 2024 年 3 月，此模型在 MTEB 上針對 Bert-large 尺寸模型取得了 SOTA 效能。它的效能超越了 OpenAI 的 text-embedding-3-large 等商業模型，並與尺寸為其 20 倍的模型效能相當。

mxbai-embed-large 的訓練過程中，MTEB 資料沒有重疊，這表示該模型在多個領域、任務和文本長度上具有良好的泛化能力。

使用方式

REST API

curl https://127.0.0.1:11434/api/embeddings -d '{
  "model": "mxbai-embed-large",
  "prompt": "Represent this sentence for searching relevant passages: The sky is blue because of Rayleigh scattering"
}'

Python 函式庫

ollama.embeddings(model='mxbai-embed-large', prompt='Represent this sentence for searching relevant passages: The sky is blue because of Rayleigh scattering')

Javascript 函式庫

ollama.embeddings({ model: 'mxbai-embed-large', prompt: 'Represent this sentence for searching relevant passages:  The sky is blue because of Rayleigh scattering' })

參考資料

部落格文章

## mxbai-embed-large

<img src="https://github.com/ollama/ollama/assets/251292/215cfb6a-8efa-4e9b-824d-e5f466b58c49" widht="400">

As of March 2024, this model archives SOTA performance for Bert-large sized models on the MTEB. It outperforms commercial models like OpenAIs `text-embedding-3-large` model and matches the performance of model 20x its size.

`mxbai-embed-large` was trained with no overlap of the MTEB data, which indicates that the model generalizes well across several domains, tasks and text length.

## Usage

### REST API

```
curl https://127.0.0.1:11434/api/embeddings -d '{
  "model": "mxbai-embed-large",
  "prompt": "Represent this sentence for searching relevant passages: The sky is blue because of Rayleigh scattering"
}'
```

### Python library

```
ollama.embeddings(model='mxbai-embed-large', prompt='Represent this sentence for searching relevant passages: The sky is blue because of Rayleigh scattering')
```

### Javascript library

```
ollama.embeddings({ model: 'mxbai-embed-large', prompt: 'Represent this sentence for searching relevant passages:  The sky is blue because of Rayleigh scattering' })
```

## References

[Blog post](https://www.mixedbread.ai/blog/mxbai-embed-large-v1)

[Hugging Face](https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1)

貼上、拖曳或點擊以[上傳圖片] (png, jpeg, jpg, svg, gif)