Update app.py

app.py

@@ -129,9 +129,9 @@ def main():
         model_args = parser.parse_args_into_dataclasses()[0]
 
     tokenizer = AutoTokenizer.from_pretrained(
-        model_args.model_name_or_path, trust_remote_code=True)
+        "THUDM/chatglm-6b-int4", trust_remote_code=True)
     config = AutoConfig.from_pretrained(
-        model_args.model_name_or_path, trust_remote_code=True)
+        "MOSS550V/divination", trust_remote_code=True)
 
     config.pre_seq_len = model_args.pre_seq_len
     config.prefix_projection = model_args.prefix_projection
@@ -148,7 +148,7 @@ def main():
                 new_prefix_state_dict[k[len("transformer.prefix_encoder."):]] = v
         model.transformer.prefix_encoder.load_state_dict(new_prefix_state_dict)
     else:
-        model = AutoModel.from_pretrained(model_args.model_name_or_path, config=config, trust_remote_code=True)
+        model = AutoModel.from_pretrained("THUDM/chatglm-6b-int4", config=config, trust_remote_code=True)
 
     if model_args.quantization_bit is not None:
         print(f"Quantized to {model_args.quantization_bit} bit")