Update app.py

app.py

@@ -21,7 +21,7 @@ model = AutoModelForCausalLM.from_pretrained(model_path, device_map='cuda', quan
 def generate_text(prompt, custom_prompt, temperature, max_length):
     structured_input = f"[[[Title]]]: {prompt}\n[[[Content]]]: {custom_prompt}"
     inputs = tokenizer(structured_input, return_tensors='pt').to('cuda')
-    generated_ids = model.generate(**inputs, max_new_tokens=max_length, temperature=temperature, pad_token_id=tokenizer.eos_token_id)
+    generated_ids = model.generate(**inputs, max_new_tokens=max_length, temperature=temperature, pad_token_id=tokenizer.eos_token_id, do_sample=True)
     generated_text = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
     return generated_text