init model and tokenizer

pilot/__init__.py

@@ -0,0 +1,3 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+__version__ = "0.0.1"

pilot/model/__init__.py

@@ -0,0 +1,2 @@
+
+from model.loader import *

pilot/model/loader.py

@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 
 import torch
-from utils import get_gpu_memory
+from pilot.utils import get_gpu_memory
 from fastchat.serve.inference import compress_module
 from transformers import (
     AutoTokenizer,

pilot/server/sqlgpt.py

@@ -1,9 +1,15 @@
 #!/usr/bin/env python3
 #-*- coding: utf-8 -*-
 
-from model.loader import ModerLoader
+from pilot.model.loader import ModerLoader
 from fastchat.serve.inference import generate_stream
-from configs.model_config import *
+from pilot.configs.model_config import *
 
 if __name__ == "__main__":
-    pass
+
+    model_path = llm_model_config[LLM_MODEL]
+
+    ml = ModerLoader(model_path)
+    model, tokenizer = ml.loader(load_8bit=True) 
+    print(model)
+    print(tokenizer)