new version

request_llm/bridge_all.py

@@ -52,6 +52,7 @@ API_URL_REDIRECT, AZURE_ENDPOINT, AZURE_ENGINE = get_conf("API_URL_REDIRECT", "A
 openai_endpoint = "https://api.openai.com/v1/chat/completions"
 api2d_endpoint = "https://openai.api2d.net/v1/chat/completions"
 newbing_endpoint = "wss://sydney.bing.com/sydney/ChatHub"
+if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
 azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
 # 兼容旧版的配置
 try:
@@ -125,6 +126,15 @@ model_info = {
         "token_cnt": get_token_num_gpt4,
     },
 
+    "gpt-4-32k": {
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": openai_endpoint,
+        "max_token": 32768,
+        "tokenizer": tokenizer_gpt4,
+        "token_cnt": get_token_num_gpt4,
+    },
+    
     # azure openai
     "azure-gpt-3.5":{
         "fn_with_ui": chatgpt_ui,
@@ -135,6 +145,15 @@ model_info = {
         "token_cnt": get_token_num_gpt35,
     },
 
+    "azure-gpt-4":{
+        "fn_with_ui": chatgpt_ui,
+        "fn_without_ui": chatgpt_noui,
+        "endpoint": azure_endpoint,
+        "max_token": 8192,
+        "tokenizer": tokenizer_gpt35,
+        "token_cnt": get_token_num_gpt35,
+    },
+
     # api_2d
     "api2d-gpt-3.5-turbo": {
         "fn_with_ui": chatgpt_ui,

request_llm/bridge_chatglm.py

@@ -3,7 +3,7 @@ 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
 
 load_message = "ChatGLM尚未加载，加载需要一段时间。注意，取决于`config.py`的配置，ChatGLM消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
@@ -48,16 +48,17 @@ class GetGLMHandle(Process):
 
         while True:
             try:
-                if self.chatglm_model is None:
-                    self.chatglm_tokenizer = AutoTokenizer.from_pretrained(_model_name_, trust_remote_code=True)
-                    if device=='cpu':
-                        self.chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True).float()
+                with ProxyNetworkActivate('Download_LLM'):
+                    if self.chatglm_model is None:
+                        self.chatglm_tokenizer = AutoTokenizer.from_pretrained(_model_name_, trust_remote_code=True)
+                        if device=='cpu':
+                            self.chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True).float()
+                        else:
+                            self.chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True).half().cuda()
+                        self.chatglm_model = self.chatglm_model.eval()
+                        break
                     else:
-                        self.chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True).half().cuda()
-                    self.chatglm_model = self.chatglm_model.eval()
-                    break
-                else:
-                    break
+                        break
             except:
                 retry += 1
                 if retry > 3: 

request_llm/bridge_llama2.py

@@ -30,7 +30,7 @@ class GetONNXGLMHandle(LocalLLMHandle):
         with open(os.path.expanduser('~/.cache/huggingface/token'), 'w') as f:
             f.write(huggingface_token)
         model_id = 'meta-llama/Llama-2-7b-chat-hf'
-        with ProxyNetworkActivate():
+        with ProxyNetworkActivate('Download_LLM'):
             self._tokenizer = AutoTokenizer.from_pretrained(model_id, use_auth_token=huggingface_token)
             # use fp16
             model = AutoModelForCausalLM.from_pretrained(model_id, use_auth_token=huggingface_token).eval()

request_llm/requirements_chatglm.txt

@@ -1,5 +1,4 @@
 protobuf
-transformers>=4.27.1
 cpm_kernels
 torch>=1.10
 mdtex2html

request_llm/requirements_chatglm_onnx.txt

@@ -1,5 +1,4 @@
 protobuf
-transformers>=4.27.1
 cpm_kernels
 torch>=1.10
 mdtex2html

request_llm/requirements_jittorllms.txt

@@ -2,6 +2,5 @@ jittor >= 1.3.7.9
 jtorch >= 0.1.3
 torch
 torchvision
-transformers==4.26.1
 pandas
 jieba

request_llm/requirements_moss.txt

@@ -1,5 +1,4 @@
 torch
-transformers==4.25.1
 sentencepiece
 datasets
 accelerate