Update app_models/gpt_MODEL.py

app_models/gpt_MODEL.py

@@ -10,7 +10,7 @@ model = GPT2LMHeadModel.from_pretrained(model_path)
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 model.to(device)
 
-def generate_text(prompt_text, length, temperature):
+def generate_text(prompt_text, length, temperature, beams):
     encoded_prompt = tokenizer.encode(prompt_text, add_special_tokens=False, return_tensors="pt")
     encoded_prompt = encoded_prompt.to(device)
     
@@ -22,7 +22,7 @@ def generate_text(prompt_text, length, temperature):
         top_p=0.9,
         repetition_penalty=1.2,
         do_sample=True,
-        num_return_sequences=1,
+        num_return_sequences=beams,
     )
     
     # Decode the generated text