Update model.py

model.py

@@ -1,14 +1,14 @@
 from transformers import pipeline
-import transformers
-import torch
-import torch.nn as nn
-import tensorflow as tf
-from transformers import TFGPT2LMHeadModel ,GPT2Tokenizer, BitsAndBytesConfig
-tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
-model = TFGPT2LMHeadModel.from_pretrained('gpt2',pad_token_id = tokenizer.eos_token_id)
-def generate_text(inp):
-  input_ids = tokenizer.encode(inp,return_tensors = 'tf')
-  beam_output =  model.generate(input_ids, max_length = 100,num_beams = 5, no_repeat_ngram_size = 2, early_stopping = True)
-  output = tokenizer.decode(beam_output[0],skip_special_tokens = True, clean_up_tokenization_spaces = True)
-  return ".".join(output.split(".")[:-1]) + "."
-qa_pipeline = pipeline("question-answering", model=model)
+# import transformers
+# import torch
+# import torch.nn as nn
+# import tensorflow as tf
+# from transformers import TFGPT2LMHeadModel ,GPT2Tokenizer, BitsAndBytesConfig
+# tokenizer = GPT2Tokenizer.from_pretrained('gpt2')
+# model = TFGPT2LMHeadModel.from_pretrained('gpt2',pad_token_id = tokenizer.eos_token_id)
+# def generate_text(inp):
+#   input_ids = tokenizer.encode(inp,return_tensors = 'tf')
+#   beam_output =  model.generate(input_ids, max_length = 100,num_beams = 5, no_repeat_ngram_size = 2, early_stopping = True)
+#   output = tokenizer.decode(beam_output[0],skip_special_tokens = True, clean_up_tokenization_spaces = True)
+#   return ".".join(output.split(".")[:-1]) + "."
+qa_pipeline = pipeline("question-answering", model='deepset/roberta-base-squad2')