llm-finetuner 0.1.1

A package for fine-tuning and quantizing language models

Finetuner Module

This module contains functions for fine-tuning language models, merging models, and uploading models to Hugging Face

1. train_model: Used for fine-tuning a language model on a specific dataset.
2. merge_model: Allows merging of a base model with a fine-tuned model.
3. upload_to_hf: Handles uploading models to the Hugging Face model hub.

Quantise Module

This module provides functionality for quantizing models and uploading the quantized versions

1. run_quantization: Performs quantization on a given model to reduce its size.
2. run_upload: Uploads a quantized model to Hugging Face.