|
---
|
|
base_model: unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit
|
|
language:
|
|
- en
|
|
license: mit
|
|
tags:
|
|
- text-generation-inference
|
|
- transformers
|
|
- unsloth
|
|
- llama
|
|
- trl
|
|
- sft
|
|
datasets:
|
|
- ai-maker-space/acronyms_and_initialisms_translated
|
|
---
|
|
|
|
## Overview |
|
|
|
This model is a fine-tuned version of the **Meta LLaMA 3.1 8B Instruct** model. |
|
It has been fine-tuned using the [Unsloth library](https://huggingface.co/unsloth) with **4-bit quantization** for efficient inference and deployment. |
|
The fine-tuning process utilized a synthetic dataset from **@AI Maker Space** consisting of acronyms and their expanded forms in English and was performed using the LoRA (Low-Rank Adaptation) technique, specifically designed for instruction-based tasks. |
|
It can be easily deployed in low-resource environments thanks to the 4-bit quantization. |
|
|
|
|
|
|
|
# Uploaded model |
|
|
|
- **Developed by:** vhab10 |
|
- **License:** apache-2.0 |
|
- **Finetuned from model :** unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit |
|
|
|
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
