---
license: llama3.2
tags:
- llama.cpp
- gguf
- query-expansion
datasets:
- s-emanuilov/query-expansion
base_model:
- meta-llama/Llama-3.2-3B-GGUF
---
# Query Expansion GGUF - based on Llama-3.2-3B

GGUF quantized version of Llama-3.2-3B for query expansion task.
Part of a collection of query expansion models available in different architectures and sizes.

## Overview

**Task:** Search query expansion  
**Base model:** [Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)  
**Training data:** [Query Expansion Dataset](https://huggingface.co/datasets/s-emanuilov/query-expansion)  

<img src="static/query-expansion-model.jpg" alt="Query Expansion Model" width="600px" />

## Quantized Versions

Model available in multiple quantization formats:
- F16 (Original size)
- Q8_0 (~8-bit quantization) 
- Q5_K_M (~5-bit quantization)
- Q4_K_M (~4-bit quantization)
- Q3_K_M (~3-bit quantization)

## Related Models

### Fine-tuned models
- [Qwen2.5-3B](https://huggingface.co/s-emanuilov/query-expansion-Qwen2.5-3B)
- [Qwen2.5-7B](https://huggingface.co/s-emanuilov/query-expansion-Qwen2.5-7B)
- [Llama-3.2-3B](https://huggingface.co/s-emanuilov/query-expansion-Llama-3.2-3B)

### GGUF Variants  
- [Qwen2.5-3B-GGUF](https://huggingface.co/s-emanuilov/query-expansion-Qwen2.5-3B-GGUF)
- [Qwen2.5-7B-GGUF](https://huggingface.co/s-emanuilov/query-expansion-Qwen2.5-7B-GGUF)

## Details
This model is designed for enhancing search and retrieval systems by generating semantically relevant query expansions.

It could be useful for:
- Advanced RAG systems
- Search enhancement
- Query preprocessing 
- Low-latency query expansion

## Example

**Input:** "apple stock"
**Expansions:**
- "apple market"
- "apple news"
- "apple stock price"
- "apple stock forecast"

## Citation

If you find my work helpful, feel free to give me a citation.

```