app

app.py

@@ -16,7 +16,7 @@ import time,json
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
-base_model = "/fs/nexus-projects/brain_project/Llama-2-7b-chat-hf-qformer/"
+base_model = "./Llama-2-7b-chat-hf-qformer"
 
 prompter = Prompter('alpaca_short')
 tokenizer = LlamaTokenizer.from_pretrained(base_model)