Update app.py

app.py

@@ -92,14 +92,16 @@ def load_model(model_path, progress=gr.Progress()):
     
     try:
         progress(0.3, desc="Loading tokenizer...")
-        current_tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False,trust_remote_code=True,)
+        config = AutoConfig.from_pretrained(model_path, trust_remote_code=True)
+        current_tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False,trust_remote_code=True)
         
         progress(0.5, desc="Loading model...")
         current_model = AutoModelForCausalLM.from_pretrained(
             model_path, 
             device_map="auto", 
             torch_dtype=torch.float16,
-            trust_remote_code=True,
+            config=config,
+            trust_remote_code=True
         )
         
         current_model_path = model_path