Update utils.py

utils.py

@@ -68,7 +68,7 @@ def generate_prompt_with_history(text, history, tokenizer, max_length=2048):
 
 
 
-def load_tokenizer_and_model(base_model, use_auth_token, load_8bit=False):
+def load_tokenizer_and_model(base_model, load_8bit=False):
     if torch.cuda.is_available():
         device = "cuda"
     else:
@@ -80,12 +80,11 @@ def load_tokenizer_and_model(base_model, use_auth_token, load_8bit=False):
             base_model,
             load_in_8bit=load_8bit,
             torch_dtype=torch.float16,
-            device_map="auto",
-            use_auth_token=use_auth_token
+            device_map="auto"
         )
     else:
         model = AutoModelForCausalLM.from_pretrained(
-            base_model, device_map={"": device}, low_cpu_mem_usage=True, use_auth_token=use_auth_token
+            base_model, device_map={"": device}, low_cpu_mem_usage=True
         )
 
     #if not load_8bit: