update

semantic_search.py

@@ -23,8 +23,10 @@ from huggingface import dataset_utils
 
 global_data_path = os.environ.get("GLOBAL_DATA_PATH", "./legal_info_search_data/")
 
+# access token huggingface. Если задан, то используется модель с HF
 hf_token = os.environ.get("HF_TOKEN", None)
 hf_dataset = os.environ.get("HF_DATASET", None)
+hf_model_name = os.environ.get("HF_MODEL_NAME", "")
 
 if hf_token is not None and hf_dataset is not None:
     global_data_path = dataset_utils.get_global_data_path()
@@ -59,9 +61,6 @@ db_data_types = ['НКРФ', 'ГКРФ', 'ТКРФ', 'Федеральный з
 
 device = os.environ.get("MODEL_DEVICE", 'cuda' if torch.cuda.is_available() else 'cpu')
 
-# access token huggingface. Если задан, то используется модель с HF
-hf_token = os.environ.get("HF_TOKEN", "")
-hf_model_name = os.environ.get("HF_MODEL_NAME", "")
 
 llm_api_endpoint = os.environ.get("LLM_API_ENDPOINT", "")
 
@@ -405,8 +404,8 @@ class SemanticSearch:
 
     def load_model(self):
         if hf_token and hf_model_name:
-            self.tokenizer = AutoTokenizer.from_pretrained(hf_model_name, use_auth_token=True)
-            self.model = AutoModel.from_pretrained(hf_model_name, use_auth_token=True).to(self.device)
+            self.tokenizer = AutoTokenizer.from_pretrained(hf_model_name, use_auth_token=hf_token)
+            self.model = AutoModel.from_pretrained(hf_model_name, use_auth_token=hf_token).to(self.device)
         else:
             self.tokenizer = AutoTokenizer.from_pretrained(global_model_path)
             self.model = AutoModel.from_pretrained(global_model_path).to(self.device)