abir9hassini / Generating-New-Recipes-using-GPT Public

Notifications You must be signed in to change notification settings
Fork 0
Star 0

The project is about generating new recipes, the recipes are split into ingredients and instructions. Through this project, We will be finetuning a distilled version of GPT-2 on a smaller-scale dataset comprising recipes

0 stars 0 forks Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
transformers		transformers
LICENSE		LICENSE
README.md		README.md
Task1.ipynb		Task1.ipynb
Task2.ipynb		Task2.ipynb
Task3.ipynb		Task3.ipynb
Task4.ipynb		Task4.ipynb
Task5.ipynb		Task5.ipynb
Task6.ipynb		Task6.ipynb

Repository files navigation

Generating-New-Recipes-using-GPT

This project is about Generating Recipes from Ingredients using GPT2. The project is divided into following tasks:

- Task 1: An introduction to the problem, including a short demo

- Task 2: Explortory data analsysis of our data, and some basic preprocessing

- Task 3: Dataset preparation for our modeling

- Task 4: Basic usecase of distillation and GPT-2

- Task 5: Launching training on a Google Colab instance with Google Drive integration

- Task 6: Exploring how well our model generates realistic recipes

We used the Recipe box dataset which is collated by Ryan Lee, and sourced from Food Network, Epicurious, and Allrecipes.

About

The project is about generating new recipes, the recipes are split into ingredients and instructions. Through this project, We will be finetuning a distilled version of GPT-2 on a smaller-scale dataset comprising recipes

nlp deep-learning jupyter-notebook transformers datasets huggingface-transformers hugging-face large-language-models

Report repository

Releases

No releases published

Packages

No packages published

Languages

Jupyter Notebook 100.0%