70B

app.py

@@ -78,7 +78,7 @@ data = dataset
 data = data.add_faiss_index("embeddings") # column name that has the embeddings of the dataset
 
 model_id = "meta-llama/Meta-Llama-3-8B-Instruct"
-client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct")
+client = InferenceClient("meta-llama/Meta-Llama-3-70B-Instruct")
 # model_id = r"D:\Meta-Llama-3-8B-Instruct"
 
 # use quantization to lower GPU usage