Update app.py

app.py

@@ -18,7 +18,7 @@ infer_prompt = """Li jêr rêwerzek heye ku peywirek rave dike, bi têketinek ku
 """
 
 snapshot_download("nazimali/Mistral-Nemo-Kurdish")
-snapshot_download(repo_id=model_id)
+snapshot_download(repo_id=model_id, ignore_patterns=["*.gguf"])
 
 
 @spaces.GPU
@@ -52,7 +52,7 @@ def respond(
         return_tensors="pt",
         add_special_tokens=False,
         return_token_type_ids=False,
-    )
+    ).to("cuda")
 
     with torch.inference_mode():
         generated_ids = model.generate(