I am looking for this model to fine-tune my own data (such as medical science) and after the training, I want it to be able to answer the questions. Then I am not looking for the "extractive answers" where it returns the start and end sequence (which is pretty much related to the given context scenario) but a "generative case" where I train the model with my data and then answer the question, and from its (the model's) own understanding for my data, it should be able to give me the answers.
Please let me know if anybody knows how to achieve that with this model!
Thank you so much 🤗
Hey @AayushShah! Thanks for your question. Unfortunately, this model only works with extractive answers. If you would like to have generative answers I would recommend checking out models labeled as Text Generation or Text2Text Generation. You might be interested to try out a model like BioGPT-Large-PubMedQA from Microsoft, which is a generative model that has been trained on medical data. And one of the tasks it was trained to do is question answering.