question and answer model ipynb file

backend/law_ai_qna.py

-import torch
-import numpy as np
-import pandas as pd
-from torch.utils.data import Dataset
-from transformers import TrainingArguments, Trainer
-from sklearn.model_selection import train_test_split
-from transformers import OpenAIGPTTokenizer, OpenAIGPTModel
-
-data_path = 'data/qna-summarization.xlsx'
-df = pd.read_excel(data_path)
-Answers = df['Answer'].tolist()
-Question = df['Question'].tolist()
-
-tokenizer = OpenAIGPTTokenizer.from_pretrained('openai-gpt')
-tokenizer.add_special_tokens({'pad_token': '[PAD]'})
-
-model = OpenAIGPTModel.from_pretrained('openai-gpt')
-
-question_encoding = tokenizer(Question, return_tensors='pt', padding=True, truncation=True)
-answer_encoding = tokenizer(Answers, return_tensors='pt', padding=True, truncation=True)
-
-class QnADataset(Dataset):
-    def __init__(self, question_encoding, answer_encoding):
-        self.question_encoding = question_encoding
-        self.answer_encoding = answer_encoding
-    def __getitem__(self, idx):
-        return self.question_encoding[idx], self.answer_encoding[idx]
-    def __len__(self):
-        return len(self.question_encoding)
-
-dataset = QnADataset(question_encoding, answer_encoding)
-
-training_args = TrainingArguments(
-                                output_dir='Question n Answering',          # output directory
-                                num_train_epochs=1,                                 # total # of training epochs
-                                per_device_train_batch_size=100,                      # batch size per device during training
-                                per_device_eval_batch_size=100,                       # batch size for evaluation
-                                warmup_steps=500,                                   # number of warmup steps for learning rate scheduler
-                                weight_decay=0.01,                                  # strength of weight decay
-                                logging_dir='Question n Answering/logs',            # directory for storing logs
-                                logging_steps=10
-                            )
-
-trainer = Trainer(
-                model=model,                         # the instantiated 🤗 Transformers model to be trained
-                args=training_args,                  # training arguments, defined above
-                train_dataset=dataset                # evaluation dataset
-            )
-
-trainer.train()
\ No newline at end of file