Update app.py

app.py

@@ -14,7 +14,7 @@ def generate_text(system_prompt, user_prompt, temperature, max_length, min_lengt
 
     inputs = tokenizer(tokenized_chat, return_tensors="pt").to(model.device) 
 
-    outputs = model.generate(**inputs, use_cache=True, max_length=max_length, min_length=min_length, temperature=temperature, num_return_sequences=1)
+    outputs = model.generate(**inputs, use_cache=True, max_length=max_length, min_length=min_length, temperature=temperature, num_return_sequences=1, do_sample=True)
 
     generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)