File size: 1,243 Bytes
3054086 cf362a9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 |
Covid 19 question answering data obtained from [covid_qa_deepset](https://huggingface.co/datasets/covid_qa_deepset).
Repository for the fine tuning, inference and evaluation scripts can be found [here](https://github.com/abhijithneilabraham/Covid-QA).
```
import torch
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("abhijithneilabraham/longformer_covid_qa")
model = AutoModelForQuestionAnswering.from_pretrained("abhijithneilabraham/longformer_covid_qa")
text = "Huggingface has democratized NLP. Huge thanks to Huggingface for this."
question = "What has Huggingface done ?"
encoding = tokenizer(question, text, return_tensors="pt")
input_ids = encoding["input_ids"]
# default is local attention everywhere
# the forward method will automatically set global attention on question tokens
attention_mask = encoding["attention_mask"]
start_scores, end_scores = model(input_ids, attention_mask=attention_mask)
all_tokens = tokenizer.convert_ids_to_tokens(input_ids[0].tolist())
answer_tokens = all_tokens[torch.argmax(start_scores) :torch.argmax(end_scores)+1]
answer = tokenizer.decode(tokenizer.convert_tokens_to_ids(answer_tokens))
# output => democratized NLP
``` |