chore: run black against modified code

pilot/configs/model_config.py

@@ -43,9 +43,8 @@ LLM_MODEL_CONFIG = {
     "guanaco-33b-merged": os.path.join(MODEL_PATH, "guanaco-33b-merged"),
     "falcon-40b": os.path.join(MODEL_PATH, "falcon-40b"),
     "gorilla-7b": os.path.join(MODEL_PATH, "gorilla-7b"),
-
     # TODO Support baichuan-7b
-    #"baichuan-7b" : os.path.join(MODEL_PATH, "baichuan-7b"),
+    # "baichuan-7b" : os.path.join(MODEL_PATH, "baichuan-7b"),
     "gptj-6b": os.path.join(MODEL_PATH, "ggml-gpt4all-j-v1.3-groovy.bin"),
     "proxyllm": "proxyllm",
 }

pilot/model/adapter.py

@@ -32,9 +32,14 @@ class BaseLLMAdaper:
         return True
 
     def loader(self, model_path: str, from_pretrained_kwargs: dict):
-        tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False,trust_remote_code=True)
+        tokenizer = AutoTokenizer.from_pretrained(
+            model_path, use_fast=False, trust_remote_code=True
+        )
         model = AutoModelForCausalLM.from_pretrained(
-            model_path, low_cpu_mem_usage=True, trust_remote_code=True, **from_pretrained_kwargs
+            model_path,
+            low_cpu_mem_usage=True,
+            trust_remote_code=True,
+            **from_pretrained_kwargs,
         )
         return model, tokenizer
 

pilot/server/llmserver.py

@@ -90,8 +90,7 @@ class ModelWorker:
             ret = {"text": "**GPU OutOfMemory, Please Refresh.**", "error_code": 0}
             yield json.dumps(ret).encode() + b"\0"
         except Exception as e:
-            
-            msg = "{}: {}".format(str(e),traceback.format_exc())
+            msg = "{}: {}".format(str(e), traceback.format_exc())
 
             ret = {
                 "text": f"**LLMServer Generate Error, Please CheckErrorInfo.**: {msg}",