Update app.py

app.py

@@ -52,24 +52,24 @@ def chat(user_input, system_prompt, temperature, top_p, max_tokens):
     ).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
-        )
-
-    generated_tokens = output[0][inputs["input_ids"].shape[-1]:]
-
-    decoded = tokenizer.decode(
-        generated_tokens,
-        skip_special_tokens=True
+    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]:]
+
+decoded = tokenizer.decode(
+    generated_tokens,
+    skip_special_tokens=True
+)
+
 return decoded.strip()
 
 # =========================