ptuning-v2配置

configs/model_config.py

@@ -88,8 +88,6 @@ USE_PTUNING_V2 = False
 # LLM running device
 LLM_DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"
 
-# MOSS load in 8bit
-LOAD_IN_8BIT = True
 
 VS_ROOT_PATH = os.path.join(os.path.dirname(os.path.dirname(__file__)), "vector_store")
 

models/loader/loader.py

@@ -65,7 +65,7 @@ class LoaderCheckPoint:
         self.tokenizer = None
         self.model_dir = params.get('model_dir', '')
         self.lora_dir = params.get('lora_dir', '')
-        self.ptuning_dir = params.get('ptuning_dir', '')
+        self.ptuning_dir = params.get('ptuning_dir', 'ptuning-v2')
         self.cpu = params.get('cpu', False)
         self.gpu_memory = params.get('gpu_memory', None)
         self.cpu_memory = params.get('cpu_memory', None)