Update services/model_service.py

services/model_service.py

@@ -25,7 +25,7 @@ class ModelService:
     @lru_cache(maxsize=1)
     def _load_models(self):
         try:
-            self.tokenizer = AutoTokenizer.from_pretrained(settings.MODEL_NAME)
+            self.tokenizer = AutoTokenizer.from_pretrained(settings.MODEL_NAME )
 
                   # Modify the model configuration to use a valid rope_scaling format
             config = LlamaConfig.from_pretrained(settings.model_name)