Update app.py

app.py

@@ -51,17 +51,17 @@ def chat(user_input, system_prompt, temperature, top_p, max_tokens):
         return_tensors="pt"
     ).to(model.device)
 
-    with torch.no_grad():
-    output = model.generate(
-        **inputs,
-        max_new_tokens=int(max_tokens),
-        do_sample=True,
-        temperature=float(temperature),
-        top_p=float(top_p),
-        repetition_penalty=1.1,
-        eos_token_id=tokenizer.eos_token_id,
-        pad_token_id=tokenizer.eos_token_id
-    )
+        with torch.no_grad():
+        output = model.generate(
+            **inputs,
+            max_new_tokens=int(max_tokens),
+            do_sample=True,
+            temperature=float(temperature),
+            top_p=float(top_p),
+            repetition_penalty=1.1,
+            eos_token_id=tokenizer.eos_token_id,
+            pad_token_id=tokenizer.eos_token_id
+        )
 
 generated_tokens = output[0][inputs["input_ids"].shape[-1]:]