Update app.py

app.py

@@ -6,19 +6,11 @@ model_name = "ministral/Ministral-3b-instruct"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name)
 
-def generate_response(prompt, max_length=2000):
+def generate_response(prompt, max_length=400):
     inputs = tokenizer(prompt, return_tensors="pt")
-    outputs = model.generate(
-        **inputs, 
-        max_length=max_length,
-        do_sample=True,
-        temperature=0.9,
-        top_p=0.95,
-        no_repeat_ngram_size=0
-    )
+    outputs = model.generate(**inputs, max_length=max_length)
     return tokenizer.decode(outputs[0], skip_special_tokens=True)
 
-
 def chat(message, history):
     history_text = "\n".join([f"Human: {h[0]}\nAI: {h[1]}" for h in history])
     prompt = f"{history_text}\nHuman: {message}\nAI:"