embeddinggemma - Ollama 框架

embeddinggemma

965K 下载更新 7个月前

EmbeddingGemma 是 Google 的一个 300M 参数嵌入模型。

嵌入 300m

ollama pull embeddinggemma

curl https://:11434/api/embed \
  -d '{
    "model": "embeddinggemma",
    "input": "Why is the sky blue?"
  }'

import ollama

response = ollama.embed(
    model='embeddinggemma',
    input='The sky is blue because of Rayleigh scattering',
)
print(response.embeddings)

import ollama from 'ollama'

const response = await ollama.embed({
  model: 'embeddinggemma',
  input: 'The sky is blue because of Rayleigh scattering',
})
console.log(response.embeddings)

模型

查看全部 →

名称

5 个模型

大小

上下文

输入

embeddinggemma:latest

622MB · 2K 上下文窗口 · 文本 · 7个月前

embeddinggemma:latest

622MB

2K

文本

embeddinggemma:300m

622MB · 2K 上下文窗口 · 文本 · 7个月前

embeddinggemma:300m 最新

622MB

2K

文本

自述文件

此模型需要 Ollama v0.11.10 或更高版本

EmbeddingGemma 是一个 3 亿参数的、在同等规模下处于最先进水平的开放嵌入模型，由 Google 基于 Gemma 3（采用 T5Gemma 初始化）构建，并使用了与创建 Gemini 模型相同的研究和技术。EmbeddingGemma 生成文本的向量表示，使其非常适合搜索和检索任务，包括分类、聚类和语义相似性搜索。该模型使用 100 多种口语语言的数据进行训练。

其小尺寸和设备端重点使其能够在资源有限的环境中部署，例如手机、笔记本电脑或台式机，从而使每个人都能以民主的方式访问最先进的 AI 模型，并有助于促进创新。

基准测试

训练数据集

该模型使用包含各种来源的文本数据的训练数据集进行训练，总计约 3200 亿个 token。以下是关键组成部分

网页文档：各种各样的网页文本集合确保模型接触到广泛的语言风格、主题和词汇。训练数据集包括 100 多种语言的内容。
代码和技术文档：将模型暴露于代码和技术文档有助于其学习编程语言和专业科学内容的结构和模式，从而提高其理解代码和技术问题的能力。
合成和任务特定数据：合成训练数据有助于教会模型特定技能。这包括针对信息检索、分类和情感分析等任务的策划数据，这有助于微调其在常见嵌入应用中的性能。

这些不同数据源的结合对于训练一个功能强大的多语言嵌入模型至关重要，该模型可以处理各种不同的任务和数据格式。

参考

![image.png](/assets/library/embeddinggemma/9a20d963-4bf1-4177-9568-ca5d53a2d14e)

> This model requires [Ollama v0.11.10](https://github.com/ollama/ollama/releases/tag/v0.11.10) or later

**EmbeddingGemma** is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages.

The small size and on-device focus makes it possible to deploy in environments with limited resources such as mobile phones, laptops, or desktops, democratizing access to state of the art AI models and helping foster innovation for everyone.

### Benchmark

![image.png](/assets/library/embeddinggemma/59a205f6-1711-4db4-8026-96d23fa2c9da)

#### Training Dataset

This model was trained on a dataset of text data that includes a wide variety of sources totaling approximately 320 billion tokens. Here are the key components:

-   **Web Documents**: A diverse collection of web text ensures the model is exposed to a broad range of linguistic styles, topics, and vocabulary. The training dataset includes content in over 100 languages.
-   **Code and Technical Documents**: Exposing the model to code and technical documentation helps it learn the structure and patterns of programming languages and specialized scientific content, which improves its understanding of code and technical questions.
-   **Synthetic and Task-Specific Data**: Synthetically training data helps to teach the model specific skills. This includes curated data for tasks like information retrieval, classification, and sentiment analysis, which helps to fine-tune its performance for common embedding applications.

The combination of these diverse data sources is crucial for training a powerful multilingual embedding model that can handle a wide variety of different tasks and data formats.

### Reference 
[Documentation](https://ai.google.dev/gemma/docs/embeddinggemma)

粘贴、拖放或单击以上传图像（.png、.jpeg、.jpg、.svg、.gif）