README.md

metadata

license: mit
datasets:
  - tatsu-lab/alpaca
tags:
  - generated_from_trainer
  - text2text-generation
model-index:
  - name: T5R-base
    results: []
pipeline_tag: text2text-generation
language:
  - en
widget:
  - text: >
      Instruction: X

      Output: Adolf Hitler (German: [ˈadɔlf ˈhɪtlɐ] (listen); 20 April 1889 – 30
      April 1945) was an Austrian-born German politician who was the dictator of
      Germany from 1933 until his suicide in 1945. He rose to power as the
      leader of the Nazi Party,[a] becoming the chancellor in 1933 and then
      taking the title of Führer und Reichskanzler in 1934.[b] During his
      dictatorship, he initiated World War II in Europe by invading Poland on 1
      September 1939. He was closely involved in military operations throughout
      the war and was central to the perpetration of the Holocaust: the genocide
      of about six million Jews and millions of other victims.

      X:
    example_title: Example 1
  - text: >
      Instruction: X

      Output: 1- Base your meals on higher fibre starchy carbohydrates. 2- Eat
      lots of fruit and veg. 3- Eat more fish, including a portion of oily fish.

      What kind of instruction could this be the answer to?

      X:
    example_title: Example 2

T5-Reverse (T5R)

This model can generate prompts (instructions) for any text!

This model is an instruction-tuned version of google/flan-t5-base on alpaca dataset but in reverse format!

How to Use the Model

You can use the transformers library to load and utilize the T5-Reverse (T5R) model for generating prompts based on text. Here's an example of how to do it:

>>> # Import required libraries
>>> import torch
>>> from transformers import pipeline

>>> # Load the model and tokenizer using the pipeline from Hugging Face Hub
>>> inference = pipeline("text2text-generation", model="kargaranamir/T5R-base")

>>> # Example instruction and prompt
>>> sample = '''
>>> Instruction: X
>>> Output: 1- Base your meals on higher fibre starchy carbohydrates. 2- Eat lots of fruit and veg. 3- Eat more fish, including a portion of oily fish.
>>> What kind of instruction could this be the answer to?
>>> X:
>>> '''

>>> # Generate a response using the model
>>> res = inference(sample)

>>> # Print the generated response
>>> print(res)

[{'generated_text': 'Instruction: Generate three recommendations for a healthy diet.'}]

Citation

If you find this model/approach useful, make a link to the huggingface model.