修复本地模型在Windows下的加载BUG

request_llms/bridge_qwen.py

@@ -6,7 +6,7 @@ from transformers import AutoModel, AutoTokenizer
 import time
 import threading
 import importlib
-from toolbox import update_ui, get_conf
+from toolbox import update_ui, get_conf, ProxyNetworkActivate
 from multiprocessing import Process, Pipe
 from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
 
@@ -29,12 +29,13 @@ class GetONNXGLMHandle(LocalLLMHandle):
         import platform
         from modelscope import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
 
-        model_id = 'qwen/Qwen-7B-Chat'
-        self._tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen-7B-Chat', trust_remote_code=True, resume_download=True)
-        # use fp16
-        model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True, fp16=True).eval()
-        model.generation_config = GenerationConfig.from_pretrained(model_id, trust_remote_code=True)  # 可指定不同的生成长度、top_p等相关超参
-        self._model = model
+        with ProxyNetworkActivate('Download_LLM'):
+            model_id = 'qwen/Qwen-7B-Chat'
+            self._tokenizer = AutoTokenizer.from_pretrained('Qwen/Qwen-7B-Chat', trust_remote_code=True, resume_download=True)
+            # use fp16
+            model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", trust_remote_code=True, fp16=True).eval()
+            model.generation_config = GenerationConfig.from_pretrained(model_id, trust_remote_code=True)  # 可指定不同的生成长度、top_p等相关超参
+            self._model = model
 
         return self._model, self._tokenizer