update ignore file

app_api.py

@@ -12,6 +12,9 @@ model_name = "openlm-research/open_llama_3b_v2"
 tokenizer = LlamaTokenizer.from_pretrained(model_name)
 model = LlamaModel.from_pretrained(model_name, from_safetensors=False)
 # model.eval()
+device = "cuda" if torch.cuda.is_available() else "cpu"
+
+model = model.to(device)
 
 app = Flask(__name__)
 
@@ -23,7 +26,7 @@ def generate_embeddings():
     
     embeddings = []
     for product in products:
-        inputs = tokenizer(product["description"], return_tensors="pt", truncation=True, max_length=512)
+        inputs = tokenizer(product["description"], return_tensors="pt", truncation=True, max_length=512).to(device)
         with torch.no_grad():
             outputs = model(**inputs, output_hidden_states=True)
         embedding = outputs.hidden_states[-1].mean(dim=1).squeeze().numpy()