Update app.py

app.py

@@ -41,12 +41,14 @@ def ask():
 
     inputs = tokenizer(prompt, return_tensors="pt").to(DEVICE)
 
-    outputs = model.generate(
-        **inputs,
-        max_new_tokens=450,
-        do_sample=True,
-        temperature=1
-    )
+  outputs = model.generate(
+    **inputs,
+    max_new_tokens=80,
+    do_sample=False,
+    temperature=0.0,
+    eos_token_id=tokenizer.eos_token_id
+)
+
 
     text = tokenizer.decode(outputs[0], skip_special_tokens=True)
     reply = text.split("Assistant:")[-1].strip()