README.md

---
license: mit
---
# bge-large-en-v1.5-GGUF for llama.cpp

This repository contains a converted version of the BAAI/bge-large-en-v1.5 model for text embeddings, specifically prepared for use with the `llama.cpp` or Python `llama-cpp-python` library.

**Original Model:** [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5)

**Conversion Details:**

* The conversion was performed using `llama.cpp's convert-hf-to-gguf.py` script.
* This conversion optimizes the model for the `llama.cpp`.

**Usage:**

This model can be loaded and used for text embedding tasks using the `llama-cpp-python` library. Here's an example:

```python
from llama import Model

# Load the converted model
model = Model.load("rbehzadan/bge-large-en-v1.5-ggml-f16")

# Encode some text
text = "This is a sample sentence."
encoded_text = model.embed(text)
```

**Important Notes:**

* This converted model might have slight performance variations compared to the original model due to the conversion process.
* Ensure you have the `llama-cpp-python` library installed for this model to function.

**License:**

The license for this model is inherited from the original BAAI/bge-large-en-v1.5 model (refer to the original model's repository for details).

**Contact:**

Feel free to create an issue in this repository for any questions or feedback.