Update services/model_service.py

services/model_service.py

@@ -28,7 +28,7 @@ class ModelService:
             self.tokenizer = AutoTokenizer.from_pretrained(settings.MODEL_NAME)
 
                   # Modify the model configuration to use a valid rope_scaling format
-            config = LlamaConfig.from_pretrained(model_name)
+            config = LlamaConfig.from_pretrained(settings.model_name)
             if hasattr(config, "rope_scaling") and isinstance(config.rope_scaling, dict):
                 config.rope_scaling = {
                     "type": "linear",