metadata
license: mit
widget:
- text: 'writeWiki: Jupiter'
- text: 'writeWiki: Sri Lanka'
- text: 'writeWiki: Language Model'
language:
- en
datasets:
- wikipedia
Fine tuned T5 base model with Simple English Wikipedia Dataset
This model is fine tuned with articles from Simple English Wikipedia for article generation.
How to use
We have to use "writeWiki: " part at the begining of each prompt. Used around 25,000 articles for training.
You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:
>>> from transformers import pipeline
>>> generator = pipeline('text2text-generation', model='Suchinthana/T5-Base-Wikigen')
>>> generator("writeWiki: Microcontroller", do_sample=True, max_length=250)