1.更改加载lora的方式;2.允许api.py调用args.py的命令行;3. FastChat路径提示

api.py

@@ -583,7 +583,7 @@ if __name__ == "__main__":
     parser.add_argument("--ssl_keyfile", type=str)
     parser.add_argument("--ssl_certfile", type=str)
     # 初始化消息
-    args = None
+
     args = parser.parse_args()
     args_dict = vars(args)
     shared.loaderCheckPoint = LoaderCheckPoint(args_dict)

configs/model_config.py

@@ -32,7 +32,7 @@ EMBEDDING_DEVICE = "cuda" if torch.cuda.is_available() else "mps" if torch.backe
 # llm_model_dict 处理了loader的一些预设行为，如加载位置，模型名称，模型处理器实例
 # 在以下字典中修改属性值，以指定本地 LLM 模型存储位置
 # 如将 "chatglm-6b" 的 "local_model_path" 由 None 修改为 "User/Downloads/chatglm-6b"
-# 此处请写绝对路径
+# 此处请写绝对路径,且路径中必须包含模型名称，FastChat会根据路径名称提取repo-id
 llm_model_dict = {
     "chatglm-6b-int4-qe": {
         "name": "chatglm-6b-int4-qe",
@@ -104,17 +104,14 @@ LOAD_IN_8BIT = False
 # Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.
 BF16 = False
 # 本地lora存放的位置
-LORA_DIR = "loras/"
-
-# LLM lora path，默认为空，如果有请直接指定文件夹路径
-LLM_LORA_PATH = ""
-USE_LORA = True if LLM_LORA_PATH else False
+LORA_DIR = "./loras/"
 
 # LLM streaming reponse
 STREAMING = True
 
 # Use p-tuning-v2 PrefixEncoder
-USE_PTUNING_V2 = False
+
+PTUNING_DIR="./ptuning-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

@@ -42,7 +42,7 @@ parser.add_argument('--no-remote-model', action='store_true', help='remote in th
                                                                    'model to add the ` '
                                                                    '--no-remote-model`')
 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', type=str, action="store_true",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',action='store_true',help="whether use ptuning-v2 checkpoint")
 parser.add_argument("--ptuning-dir",type=str,default=PTUNING_DIR,help="the dir of ptuning-v2 checkpoint")