---
base_model: Llama-3.2-3B
library_name: quantllm
tags:
  - quantllm
  - generated_from_trainer
---

# Llama-3.2-3B-4bit

This model was fine-tuned using [QuantLLM](https://github.com/codewithdark-git/QuantLLM).

## Hyperparameters
The following hyperparameters were used during training:

- **format**: gguf
- **base_model**: Llama-3.2-3B