E5 Base V2 Gguf

🚀 e5-base-v2-gguf

This repository provides GGUF format files for the e5-base-v2 embedding model, enabling efficient text embedding computation with compatibility across multiple platforms.

🚀 Quick Start

Using with llama.cpp

To compute a single embedding, build llama.cpp and run:

./embedding -ngl 99 -m [filepath-to-gguf].gguf -p 'search_query: What is TSNE?'

You can also submit a batch of texts to embed, as long as the total number of tokens does not exceed the context length. Only the first three embeddings are shown by the embedding example.

texts.txt:

search_query: What is TSNE?
search_query: Who is Laurens Van der Maaten?

Compute multiple embeddings:

./embedding -ngl 99 -m [filepath-to-gguf].gguf -f texts.txt

Using with LM Studio

1. Download the 0.2.19 beta build from here: Windows MacOS Linux
2. Once installed, open the app. Search for either "ChristianAzinn" in the main search bar or go to the "Search" tab on the left menu and search the name there.
3. Select your model from those that appear (this example uses bge-small-en-v1.5-gguf) and select which quantization you want to download. Since this model is pretty small, it's recommended to choose Q8_0, if not f16/32.
4. After the model has successfully downloaded, navigate to the "Local Server" tab on the left menu and open the loader for text embedding models.
5. Select the model you just downloaded from the dropdown that appears to load it. You may need to adjust configurations in the right - side menu, such as GPU offload if it doesn't fit entirely into VRAM.
6. Hit the "Start Server" button.

Example curl request to the API endpoint:

curl http://localhost:1234/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Your text string goes here",
    "model": "model-identifier-here"
  }'

For more information, see the LM Studio text embedding documentation.

✨ Features

• High Compatibility: These files are compatible with llama.cpp as of commit 4524290e8, as well as LM Studio as of version 0.2.19.
• Multiple Quantization Options: Various quantization methods are available, allowing users to balance between file size and quality.

📦 Installation

This section mainly focuses on the usage of the model rather than traditional installation steps. For using the model with llama.cpp, you need to build llama.cpp first. For using with LM Studio, download the appropriate version from the provided links.

💻 Usage Examples

Basic Usage with llama.cpp

./embedding -ngl 99 -m [filepath-to-gguf].gguf -p 'search_query: What is TSNE?'

Advanced Usage with LM Studio

curl http://localhost:1234/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{
    "input": "Your text string goes here",
    "model": "model-identifier-here"
  }'

📚 Documentation

Original Model

• Model creator: intfloat
• Original model: e5-base-v2

Original Description

Text Embeddings by Weakly-Supervised Contrastive Pre-training. Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei, arXiv 2022

This model has 12 layers and the embedding size is 768.

Model Details

This repo contains GGUF format files for the e5-base-v2 embedding model. These files were converted and quantized with llama.cpp PR 5500, commit 34aa045de, on a consumer RTX 4090. This model supports up to 512 tokens of context.

Compatibility

These files are compatible with llama.cpp as of commit 4524290e8, as well as LM Studio as of version 0.2.19.

Explanation of Quantisation Methods

Provided Files

🔧 Technical Details

The model files are converted and quantized with llama.cpp PR 5500, commit 34aa045de, on a consumer RTX 4090. Different quantization methods are used to balance the file size and the quality of the model.

📄 License

This project is licensed under the MIT license.

Acknowledgements

Thanks to the LM Studio team and everyone else working on open - source AI.

This README is inspired by that of nomic-ai-embed-text-v1.5-gguf, another excellent embedding model, and those of the legendary TheBloke.