version 3.75 (#1702)

* Update version to 3.74

* Add support for Yi Model API (#1635)

* 更新以支持零一万物模型

* 删除newbing

* 修改config

---------

Co-authored-by: binary-husky <qingxu.fu@outlook.com>

* Refactor function signatures in bridge files

* fix qwen api change

* rename and ref functions

* rename and move some cookie functions

* 增加haiku模型，新增endpoint配置说明 (#1626)

* haiku added

* 新增haiku，新增endpoint配置说明

* Haiku added

* 将说明同步至最新Endpoint

---------

Co-authored-by: binary-husky <qingxu.fu@outlook.com>

* private_upload目录下进行文件鉴权 (#1596)

* private_upload目录下进行文件鉴权

* minor fastapi adjustment

* Add logging functionality to enable saving
conversation records

* waiting to fix username retrieve

* support 2rd web path

* allow accessing default user dir

---------

Co-authored-by: binary-husky <qingxu.fu@outlook.com>

* remove yaml deps

* fix favicon

* fix abs path auth problem

* forget to write a return

* add `dashscope` to deps

* fix GHSA-v9q9-xj86-953p

* 用户名重叠越权访问patch (#1681)

* add cohere model api access

* cohere + can_multi_thread

* fix block user access(fail)

* fix fastapi bug

* change cohere api endpoint

* explain version

* # fix com_zhipuglm.py illegal temperature problem (#1687)

* Update com_zhipuglm.py

# fix 用户在使用 zhipuai 界面时遇到了关于温度参数的非法参数错误

* allow store lm model dropdown

* add a btn to reverse previous reset

* remove extra fns

* Add support for glm-4v model (#1700)

* 修改chatglm3量化加载方式 (#1688)

Co-authored-by: zym9804 <ren990603@gmail.com>

* save chat stage 1

* consider null cookie situation

* 在点击复制按钮时激活语音

* miss some parts

* move all to js

* done first stage

* add edge tts

* bug fix

* bug fix

* remove console log

* bug fix

* bug fix

* bug fix

* audio switch

* update tts readme

* remove tempfile when done

* disable auto audio follow

* avoid play queue update after shut up

* feat: minimizing common.js

* improve tts functionality

* deterine whether the cached model is in choices

* Add support for Ollama (#1740)

* print err when doc2x not successful

* add icon

* adjust url for doc2x key version

* prepare merge

---------

Co-authored-by: Menghuan1918 <menghuan2003@outlook.com>
Co-authored-by: Skyzayre <120616113+Skyzayre@users.noreply.github.com>
Co-authored-by: XIao <46100050+Kilig947@users.noreply.github.com>
Co-authored-by: Yuki <903728862@qq.com>
Co-authored-by: zyren123 <91042213+zyren123@users.noreply.github.com>
Co-authored-by: zym9804 <ren990603@gmail.com>

request_llms/bridge_chatglm3.py

@@ -6,7 +6,6 @@ from toolbox import get_conf, ProxyNetworkActivate
 from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
 
 
-
 # ------------------------------------------------------------------------------------------------------------------------
 # 🔌💻 Local Model
 # ------------------------------------------------------------------------------------------------------------------------
@@ -23,20 +22,45 @@ class GetGLM3Handle(LocalLLMHandle):
         import os, glob
         import os
         import platform
-        LOCAL_MODEL_QUANT, device = get_conf('LOCAL_MODEL_QUANT', 'LOCAL_MODEL_DEVICE')
 
-        if LOCAL_MODEL_QUANT == "INT4":         # INT4
-            _model_name_ = "THUDM/chatglm3-6b-int4"
-        elif LOCAL_MODEL_QUANT == "INT8":       # INT8
-            _model_name_ = "THUDM/chatglm3-6b-int8"
-        else:
-            _model_name_ = "THUDM/chatglm3-6b"  # FP16
-        with ProxyNetworkActivate('Download_LLM'):
-            chatglm_tokenizer = AutoTokenizer.from_pretrained(_model_name_, trust_remote_code=True)
-            if device=='cpu':
-                chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True, device='cpu').float()
+        LOCAL_MODEL_QUANT, device = get_conf("LOCAL_MODEL_QUANT", "LOCAL_MODEL_DEVICE")
+        _model_name_ = "THUDM/chatglm3-6b"
+        # if LOCAL_MODEL_QUANT == "INT4":  # INT4
+        #     _model_name_ = "THUDM/chatglm3-6b-int4"
+        # elif LOCAL_MODEL_QUANT == "INT8":  # INT8
+        #     _model_name_ = "THUDM/chatglm3-6b-int8"
+        # else:
+        #     _model_name_ = "THUDM/chatglm3-6b"  # FP16
+        with ProxyNetworkActivate("Download_LLM"):
+            chatglm_tokenizer = AutoTokenizer.from_pretrained(
+                _model_name_, trust_remote_code=True
+            )
+            if device == "cpu":
+                chatglm_model = AutoModel.from_pretrained(
+                    _model_name_,
+                    trust_remote_code=True,
+                    device="cpu",
+                ).float()
+            elif LOCAL_MODEL_QUANT == "INT4":  # INT4
+                chatglm_model = AutoModel.from_pretrained(
+                    pretrained_model_name_or_path=_model_name_,
+                    trust_remote_code=True,
+                    device="cuda",
+                    load_in_4bit=True,
+                )
+            elif LOCAL_MODEL_QUANT == "INT8":  # INT8
+                chatglm_model = AutoModel.from_pretrained(
+                    pretrained_model_name_or_path=_model_name_,
+                    trust_remote_code=True,
+                    device="cuda",
+                    load_in_8bit=True,
+                )
             else:
-                chatglm_model = AutoModel.from_pretrained(_model_name_, trust_remote_code=True, device='cuda')
+                chatglm_model = AutoModel.from_pretrained(
+                    pretrained_model_name_or_path=_model_name_,
+                    trust_remote_code=True,
+                    device="cuda",
+                )
             chatglm_model = chatglm_model.eval()
 
         self._model = chatglm_model
@@ -46,32 +70,36 @@ class GetGLM3Handle(LocalLLMHandle):
     def llm_stream_generator(self, **kwargs):
         # 🏃‍♂️🏃‍♂️🏃‍♂️ 子进程执行
         def adaptor(kwargs):
-            query = kwargs['query']
-            max_length = kwargs['max_length']
-            top_p = kwargs['top_p']
-            temperature = kwargs['temperature']
-            history = kwargs['history']
+            query = kwargs["query"]
+            max_length = kwargs["max_length"]
+            top_p = kwargs["top_p"]
+            temperature = kwargs["temperature"]
+            history = kwargs["history"]
             return query, max_length, top_p, temperature, history
 
         query, max_length, top_p, temperature, history = adaptor(kwargs)
 
-        for response, history in self._model.stream_chat(self._tokenizer,
-                                                         query,
-                                                         history,
-                                                         max_length=max_length,
-                                                         top_p=top_p,
-                                                         temperature=temperature,
-                                                         ):
+        for response, history in self._model.stream_chat(
+            self._tokenizer,
+            query,
+            history,
+            max_length=max_length,
+            top_p=top_p,
+            temperature=temperature,
+        ):
             yield response
 
     def try_to_import_special_deps(self, **kwargs):
         # import something that will raise error if the user does not install requirement_*.txt
         # 🏃‍♂️🏃‍♂️🏃‍♂️ 主进程执行
         import importlib
+
         # importlib.import_module('modelscope')
 
 
 # ------------------------------------------------------------------------------------------------------------------------
 # 🔌💻 GPT-Academic Interface
 # ------------------------------------------------------------------------------------------------------------------------
-predict_no_ui_long_connection, predict = get_local_llm_predict_fns(GetGLM3Handle, model_name, history_format='chatglm3')
+predict_no_ui_long_connection, predict = get_local_llm_predict_fns(
+    GetGLM3Handle, model_name, history_format="chatglm3"
+)