Update app.py

app.py

@@ -41,7 +41,7 @@ def init_args():
     args = load_hyperparam(args)
 
     # args.tokenizer = Tokenizer(model_path=args.spm_model_path)
-    args.tokenizer = AutoTokenizer.from_pretrained("Linly-AI/Linly-ChatFlow", use_fast=False, trust_remote_code=True)
+    args.tokenizer = AutoTokenizer.from_pretrained("Linly-AI/Chinese-LLaMA-2-7B-hf", use_fast=False, trust_remote_code=True)
     args.vocab_size = args.tokenizer.sp_model.vocab_size()
 
 
@@ -57,8 +57,8 @@ def init_model():
 
     # device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
     # model.to(device)
-    model = AutoModelForCausalLM.from_pretrained("Linly-AI/Linly-ChatFlow", device_map="auto", torch_dtype=torch.float16, trust_remote_code=True)
-    
+    model = AutoModelForCausalLM.from_pretrained("Linly-AI/Chinese-LLaMA-2-7B-hf", device_map="auto", torch_dtype=torch.float16, trust_remote_code=True)
+    print(model)
     print(torch.cuda.max_memory_allocated() / 1024 ** 3)
     lm_generation = LmGeneration(model, args.tokenizer)