weloSai/Llama-3.2-1B-autocompletion

Llama-3.2-1B Finetuned for Question Answering Autocompletion

This repository contains a finetuned version of the unsloth/Llama-3.2-1B model, specifically trained on a Question and Answer dataset for autocompletion tasks. The model was finetuned using the LoRA technique with the Unsloth library.

Model Details

• Base Model: unsloth/Llama-3.2-1B
• Finetuning Method: LoRA (using Unsloth)
• Training Data: A custom Question and Answer dataset (details about the dataset can be added here, e.g., source, size, format).
• Task: Question Answering Autocompletion

Usage

You can load and use this model for inference using the transformers library.