Update app.py

app.py

@@ -19,8 +19,8 @@ data = dataset["train"]
 data = data.add_faiss_index("embeddings") # column name that has the embeddings of the dataset
 
 
-model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
-
+# model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
+model_id="unsloth/llama-3-8b-bnb-4bit"
 # use quantization to lower GPU usage
 bnb_config = BitsAndBytesConfig(
     load_in_4bit=True, bnb_4bit_use_double_quant=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.bfloat16