File size: 2,899 Bytes
0428e35 10e8a8b 0da9084 10e8a8b 0da9084 9072259 0da9084 0428e35 9072259 0da9084 52ad77b 0da9084 0428e35 0da9084 0428e35 0da9084 10e8a8b |
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 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
import gradio as gr
import numpy as np
import torch
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
from transformers import DistilBertTokenizer, TFDistilBertForQuestionAnswering
# Load model & tokenizer
# model_name = "deepset/roberta-base-squad2"
# model_name = "AmazonScience/qanlu"
# model_name = 'distilbert-base-cased-distilled-squad'
model_name = "bert-large-uncased-whole-word-masking-finetuned-squad"
# tokenizer = AutoTokenizer.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
tokenizer = AutoTokenizer.from_pretrained(model_name)
# tokenizer = DistilBertTokenizer.from_pretrained(model_name)
# model = TFDistilBertForQuestionAnswering.from_pretrained(model_name)
# model = AutoModelForQuestionAnswering.from_pretrained("bert-large-uncased-whole-word-masking-finetuned-squad")
model = AutoModelForQuestionAnswering.from_pretrained(model_name)
def QA_function(context, question):
inputs = tokenizer(question, context, add_special_tokens=True, return_tensors="pt") # pt for PyTorch tf for tensorflow
input_ids = inputs["input_ids"].tolist()[0]
outputs = model(**inputs)
answer_start_scores = outputs.start_logits
answer_end_scores = outputs.end_logits
## following for torch
# Get the most likely beginning of answer with the argmax of the score
answer_start_index = torch.argmax(answer_start_scores)
# Get the most likely end of answer with the argmax of the score
answer_end_index = torch.argmax(answer_end_scores) + 1
answer = tokenizer.convert_tokens_to_string(tokenizer.convert_ids_to_tokens(input_ids[answer_start_index:answer_end_index]))
return answer
# gradio_ui = gr.Interface(QA_function, [gr.inputs.Textbox(lines=7, label="Context"), gr.inputs.Textbox(label="Question")], gr.outputs.Textbox(label="Answer"))
# a) Get predictions
nlp = pipeline('question-answering', model=model_name, tokenizer=model_name)
fixed_context = """Ishaan is 6 year old kid. he is very good in football. He is very good sports person.
he is smart kid. He can run very fast. as fast as 10 meters in 1 minute.
He goes to Vidyani ketan school. He goes to school from 8 am to 3:30 pm.
Ishaan has many friends. Vineet is Ishaan's brother. """
# def get_answer(fixed_context,question):
# QA_input = {
# 'question': question,
# 'context': fixed_context
# }
# res = nlp(QA_input)
# return res['answer']
def get_answer(question):
QA_input = {
'question': question,
'context': fixed_context
}
res = nlp(QA_input)
return res['answer']
# gradio_ui = gr.Interface(get_answer, [gr.inputs.Textbox(lines=7, label="Context"), gr.inputs.Textbox(label="Question")], gr.outputs.Textbox(label="Answer"))
gradio_ui = gr.Interface(get_answer, [gr.inputs.Textbox(label="Question")], gr.outputs.Textbox(label="Answer"))
gradio_ui.launch()
|