Update app.py

app.py

@@ -34,12 +34,12 @@ model_id = "google/gemma-3-270m-it"
 tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True,)
 model = AutoModelForCausalLM.from_pretrained(
     model_id,
+    torch_dtype="auto",
     device_map="auto",
-    torch_dtype=torch.bfloat16,
-    attn_implementation="eager",
+    attn_implementation="eager"
 )
-model.config.sliding_window = 4096
-model.eval()
+# model.config.sliding_window = 4096
+# model.eval()
 
 
 @spaces.GPU(duration=90)