Update main.py

main.py

@@ -38,11 +38,11 @@ def read_root(data: req):
   input_text = data.prompt
   
   # Tokenize the input text
-  input_ids = tokenizer.encode_plus(history_string, input_text, return_tensors="pt")
+  inputs = tokenizer.encode_plus(history_string, input_text, return_tensors="pt")
   
   # Generate output using the model
-  output_ids = model.generate(input_ids, num_beams=5, no_repeat_ngram_size=2)
-  generated_text = tokenizer.decode(output_ids[0], skip_special_tokens=True).strip()
+  outputs = model.generate(**inputs)
+  generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True).strip()
   
   answer_data = { "answer": generated_text }
   print("Answer:", generated_text)