This is the roberta-base model, fine-tuned using the SQuAD2.0 dataset. It's been trained on question-answer pairs, including unanswerable questions, for the task of Question Answering.
Overview
Language model: roberta-fine-tuned-squadv2 Language: English, Hindi(Upcoming) Downstream-task: Extractive QA Training data: SQuAD 2.0 Eval data: SQuAD 2.0 Code: See an example QA pipeline on Haystack Infrastructure: 4x Tesla v100
Haystack is an NLP framework by deepset. You can use this model in a Haystack pipeline to do question answering at scale (over many documents). To load the model in Haystack:
python
1reader = FARMReader(model_name_or_path="deepset/roberta-base-squad2")2# or 3reader = TransformersReader(model_name_or_path="deepset/roberta-base-squad2",tokenizer="deepset/roberta-base-squad2")
1from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
23model_name ="deepset/roberta-base-squad2"45# a) Get predictions6nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)7QA_input ={8'question':'Why is model conversion important?',9'context':'The option to convert models between FARM and transformers gives freedom to the user and let people easily switch between frameworks.'10}11res = nlp(QA_input)1213# b) Load model & tokenizer14model = AutoModelForQuestionAnswering.from_pretrained(model_name)15tokenizer = AutoTokenizer.from_pretrained(model_name)
deepset is the company behind the open-source NLP framework Haystack which is designed to help you build production ready NLP systems that use: Question answering, summarization, ranking etc.
