Merge branch 'dev' of github.com:hzg0601/langchain-ChatGLM-annotation into dev

git pull origin dev.

models/loader/args.py

@@ -44,7 +44,7 @@ parser.add_argument('--no-remote-model', action='store_true', help='remote in th
 parser.add_argument('--model-name', type=str, default=LLM_MODEL, help='Name of the model to load by default.')
 parser.add_argument('--lora', type=str, help='Name of the LoRA to apply to the model by default.')
 parser.add_argument("--lora-dir", type=str, default=LORA_DIR, help="Path to directory with all the loras")
-parser.add_argument('--use-ptuning-v2',type=str,default=False,help="whether use ptuning-v2 checkpoint")
+parser.add_argument('--use-ptuning-v2',type=str,default=USE_PTUNING_V2,help="whether use ptuning-v2 checkpoint")
 parser.add_argument("--ptuning-dir",type=str,default=PTUNING_DIR,help="the dir of ptuning-v2 checkpoint")
 # Accelerate/transformers
 parser.add_argument('--load-in-8bit', action='store_true', default=LOAD_IN_8BIT,