ba2512005
commented
5 months ago Based on the ERROR: [Errno 10048] error while attempting to bind on address ('::1', 9600, 0, 0): normalerweise darf jede socketadresse (protokoll, netzwerkadresse oder anschluss) nur jeweils einmal verwendet werden
It seems like your port 9600 is already being used. Perhaps you didn't shut down the application correctly last time. Please restart your computer and try again. Also browse to your Documents folder and delete the file in the config folder called local_config.yaml
The newer versions have issues with using old config files.
WiNeTel
Expected Behavior
with every update you make my lollms working less, it´s start with barly accept my GPU´s in mode balanced or auto only use ~2gig VRAM of one GPU, the rest go in Memory giving up to try to load with GPU, CPU was still working. Next update, get only 1 Answer in the Chat,with the 2. Answer is terminating the program, press any key... your last update get model loded, don´t get any answer at all, only this:
Exception in thread Thread-XX (run_llmodel_prompt): The Tread number change Traceback (most recent call last): File "G:\AI\lollms\installer_files\lollms_env\Lib\threading.py", line 1045, in _bootstrap_inner self.run() File "G:\AI\lollms\installer_files\lollms_env\Lib\threading.py", line 982, in run self._target(*self._args, **self._kwargs) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\gpt4all\_pyllmodel.py", line 373, in run_llmodel_prompt self.prompt_model(prompt, callback, **kwargs) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\gpt4all\_pyllmodel.py", line 344, in prompt_model llmodel.llmodel_prompt( OSError: exception: access violation writing 0x0000000000000140 Drücken Sie eine beliebige Taste . . .inside the console i can see, that he starting generate a answer, but this answer newer never finish, program freeze!When i try to restart from WebUI i get this Error:
ERROR: [Errno 10048] error while attempting to bind on address ('::1', 9600, 0, 0): normalerweise darf jede socketadresse (protokoll, netzwerkadresse oder anschluss) nur jeweils einmal verwendet werden INFO: Waiting for application shutdown. INFO: Application shutdown complete. ERROR: Exception in ASGI application Traceback (most recent call last): File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\uvicorn\protocols\http\h11_impl.py", line 412, in run_asgi result = await app( # type: ignore[func-returns-value] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\uvicorn\middleware\proxy_headers.py", line 84, in __call__ return await self.app(scope, receive, send) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\engineio\async_drivers\asgi.py", line 67, in __call__ await self.other_asgi_app(scope, receive, send) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\fastapi\applications.py", line 1054, in __call__ await super().__call__(scope, receive, send) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\starlette\applications.py", line 123, in __call__ await self.middleware_stack(scope, receive, send) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\starlette\middleware\errors.py", line 164, in __call__ await self.app(scope, receive, _send) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\starlette\middleware\exceptions.py", line 62, in __call__ await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\starlette\_exception_handler.py", line 53, in wrapped_app await app(scope, receive, sender) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\starlette\routing.py", line 758, in __call__ await self.middleware_stack(scope, receive, send) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\starlette\routing.py", line 778, in app await route.handle(scope, receive, send) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\starlette\routing.py", line 299, in handle await self.app(scope, receive, send) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\starlette\routing.py", line 79, in app await wrap_app_handling_exceptions(app, request)(scope, receive, send) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\starlette\_exception_handler.py", line 53, in wrapped_app await app(scope, receive, sender) File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\starlette\routing.py", line 74, in app response = await func(request) ^^^^^^^^^^^^^^^^^^^ File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\fastapi\routing.py", line 294, in app raw_response = await run_endpoint_function( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\fastapi\routing.py", line 191, in run_endpoint_function return await dependant.call(**values) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\AI\lollms\lollms-webui\endpoints\lollms_webui_infos.py", line 60, in restart_program lollmsElfServer.run_restart_script(lollmsElfServer.args) File "G:\AI\lollms\lollms-webui\lollms_webui.py", line 351, in run_restart_script sys.exit(0) SystemExit: 0 INFO: 127.0.0.1:50412 - "GET /restart_program HTTP/1.1" 500 Internal Server Error Task exception was never retrieved future: <Task finished name='Task-199' coro=<AsyncServer.shutdown() done, defined at G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\socketio\async_server.py:431> exception=TypeError("object NoneType can't be used in 'await' expression")> Traceback (most recent call last): File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\socketio\async_server.py", line 438, in shutdown await self.eio.shutdown() File "G:\AI\lollms\installer_files\lollms_env\Lib\site-packages\engineio\async_server.py", line 345, in shutdown await self.service_task_handle TypeError: object NoneType can't be used in 'await' expressionBut i can Still use the Web UI, looks like he never shutdown!When i Start completly new, i don´t get a error, but how i say a can´t use it!
Sometimes he write in the console, that is missing the \DATA\user_infos\default_user.svg Have checked the folder is empty
When Activate Long term memory in the Config, get this message in the Console: Couldn't add long term memory information to the context. Please verify the vector database
even new installation not solve, starting with the same problems. ! try different Models and different Bindings, alltime the same Error Try Models in GGUF, GGML and gptq Bindings i try was gpt4all, hugging face, exllama v2 and with Python LLAMA Cpp, get the same error like Issue #492
Supermicro dual CPU 2x14 cores, 64 GB Memory 1 Tesla P40 24GB VRAM 1 GTX 1060 6 GB VRAM, only used to install Programs local
Current Behavior
Please describe the behavior you are currently experiencing.
Steps to Reproduce
Install the program choose the Binding, the Model and the trouble begin
Possible Solution
no idea, there are no log files lollms detect my videocards is shown in System status, but never get runing the Driver, i try both Nvidea with and without Tensos in Main config and in the Binding Auto, balanced, GPU, nothing helped. tomorrow , hmm later try again a new installation! but this time will try the Manual way without win_install.bat