/Kaggle-LLM_Prompt_Recovery

LLMs are commonly used to rewrite or make stylistic changes to text. The goal is to recover the LLM prompt that was used to transform a given text.

Primary LanguageJupyter Notebook

This Repo is for Kaggle - LLM Prompt Recovery

Python Environment

1. Install Packages

pip install -r requirements.txt

Prepare Data

1. Set Kaggle Api

export KAGGLE_USERNAME="your_kaggle_username"
export KAGGLE_KEY="your_api_key"

2. Download Dataset

cd datasets
kaggle datasets download -d lizhecheng/lzc-llm-prompt-recovery-dataset
unzip lzc-llm-prompt-recovery-dataset.zip
kaggle datasets download -d lizhecheng/llm-prompt-recovery-extra-dataset
unzip llm-prompt-recovery-extra-dataset.zip
kaggle competitions download -c llm-prompt-recovery
unzip llm-prompt-recovery.zip

Train Model

You can use different ipynb or py files to do it. (However, there is a problem with very huge loss while fine-tuning gemma-7b)