Modelpublic

Nnobody/nigerian-food-gpt2

sourceHugging Facemitupdated 2y agoView on Hugging Face

0likes17downloads

Model Card

language: en tags:

—gpt2
—text-generation
—nigerian-cuisine license: mit ---

Nigerian Food GPT-2 Model

This model is fine-tuned on a dataset of Nigerian food items. It can generate descriptions of Nigerian dishes, including ingredients, health information, and regional origin.

Model Details

—Fine-tuned from: GPT-2 (small)
—Type: Language Model
—Language: English
—License: MIT

Intended Use

This model is intended for generating descriptions of Nigerian food items. It can be used for educational purposes, menu generation, or exploring Nigerian cuisine.

Training Data

The model was fine-tuned on a dataset of 100+ Nigerian food items, including information on the food's name, main ingredients, description, health rating, food class, region of origin, spice level, and price range.

Limitations

—The model's knowledge is limited to the training data provided.
—It may occasionally generate inaccurate or inconsistent information.
—The model should not be used as a definitive source for nutritional or health information.

Usage

'''python from transformers import GPT2LMHeadModel, GPT2Tokenizer

model = GPT2LMHeadModel.frompretrained("your-username/nigerian-food-gpt2") tokenizer = GPT2Tokenizer.frompretrained("your-username/nigerian-food-gpt2")

prompt = "Name: Jollof Rice" inputids = tokenizer.encode(prompt, returntensors="pt") output = model.generate(inputids, maxlength=200, numreturnsequences=1, norepeatngramsize=2) generatedtext = tokenizer.decode(output[0], skipspecialtokens=True) print(generated_text)