Update README.md

README.md

@@ -167,7 +167,7 @@ PROMPT = ">>> "
 
 def load_tokenizer(path: str):
     print("Loading tokenizer...", path)
-    tok = AutoTokenizer.from_pretrained(path, use_fast=True, local_files_only=True)
+    tok = AutoTokenizer.from_pretrained(path, use_fast=True, local_files_only=False)
     if tok.pad_token is None:
         if getattr(tok, "eos_token", None) is not None:
             tok.add_special_tokens({"pad_token": tok.eos_token})
@@ -181,14 +181,14 @@ def load_model(path: str, device: str):
     model = None
     try:
         desired_dtype = torch.float16 if device.startswith("cuda") else torch.float32
-        model = MistralForCausalLM.from_pretrained(path, local_files_only=True, dtype=desired_dtype)
+        model = MistralForCausalLM.from_pretrained(path, local_files_only=False, dtype=desired_dtype)
         print("Loaded with dtype arg.")
     except TypeError:
-        model = MistralForCausalLM.from_pretrained(path, local_files_only=True)
+        model = MistralForCausalLM.from_pretrained(path, local_files_only=False)
         print("Loaded without dtype; will convert.")
     except Exception as e:
         print("Load warning, retrying without dtype:", e)
-        model = MistralForCausalLM.from_pretrained(path, local_files_only=True)
+        model = MistralForCausalLM.from_pretrained(path, local_files_only=False)
 
     try:
         model.to(device)