add ptuning-v2 dir

configs/model_config.py

@@ -87,6 +87,12 @@ llm_model_dict = {
         "local_model_path": None,
         "provides": "MOSSLLM"
     },
+    "moss-int4": {
+        "name": "moss",
+        "pretrained_model_name": "fnlp/moss-moon-003-sft-int4",
+        "local_model_path": None,
+        "provides": "MOSSLLM"
+    },
     "vicuna-13b-hf": {
         "name": "vicuna-13b-hf",
         "pretrained_model_name": "vicuna-13b-hf",
@@ -197,6 +203,7 @@ STREAMING = True
 
 # Use p-tuning-v2 PrefixEncoder
 USE_PTUNING_V2 = False
+PTUNING_DIR='./ptuing-v2'
 
 # LLM running device
 LLM_DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backends.mps.is_available() else "cpu"

models/loader/args.py

@@ -43,6 +43,8 @@ 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("--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,