h2oai / h2ogpt

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/
http://h2o.ai
Apache License 2.0
11.32k stars 1.24k forks source link

Get a lot of Errors in Webinterface #1835

Closed DrNokkel closed 2 weeks ago

DrNokkel commented 1 month ago

I got these Error Signs and cant do anything on the webinterface.

Before I started to ge along with the webinterface i tested it in the cli which worked nicely. python generate.py --base_model=h2oai/h2ogpt-4096-llama2-7b-chat --score_model=None --prompt_type=human_bot --cli=True

It`s my first time to work with such project I hope someone can help me

image

(h2ogpt) C:\Windows\System32\h2ogpt>python generate.py --share=False --gradio_offline_level=1 --base_model=h2oai/h2ogpt-4096-llama2-7b-chat --score_model=None --prompt_type=human_bot --load_8bit=True Fontconfig error: Cannot load default config file: No such file: (null) C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydub\utils.py:170: RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning) Must install langchain for transcription, disabling Using Model h2oai/h2ogpt-4096-llama2-7b-chat git failed to run: [WinError 2] The system cannot find the file specified Must install langchain for preloading embedding model, disabling Must install DocTR and LangChain installed if enabled DocTR, disabling Starting get_model: h2oai/h2ogpt-4096-llama2-7b-chat C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\huggingface_hub\file_download.py:1150: FutureWarning: resume_download is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use force_download=True. warnings.warn( device_map: {'': 0} Loading checkpoint shards: 100%|██████████████████████████████████████████████████████| 2/2 [00:07<00:00, 3.81s/it] C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\huggingface_hub\file_download.py:1150: FutureWarning: resume_download is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use force_download=True. warnings.warn( Begin auto-detect HF cache text generation models End auto-detect HF cache text generation models Begin auto-detect llama.cpp models End auto-detect llama.cpp models Running on local URL: http://0.0.0.0:7860

To create a public link, set share=True in launch(). Started Gradio Server and/or GUI: server_name: localhost port: None Use local URL: http://localhost:7860/ C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_fields.py:160: UserWarning: Field "modellock" has conflict with protected namespace "model".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = (). warnings.warn( C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_fields.py:160: UserWarning: Field "modelinfo" has conflict with protected namespace "model".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = (). warnings.warn( C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_fields.py:160: UserWarning: Field "modelnames" has conflict with protected namespace "model".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = (). warnings.warn( verbose disabled OpenAI API URL: http://0.0.0.0:5000 OpenAI API key: EMPTY INFO: 127.0.0.1:49761 - "GET / HTTP/1.1" 200 OK INFO: 127.0.0.1:49761 - "GET /info HTTP/1.1" 200 OK INFO: 127.0.0.1:49761 - "GET /theme.css HTTP/1.1" 200 OK INFO: 127.0.0.1:49762 - "GET /heartbeat/po69u1hn4b8 HTTP/1.1" 200 OK Client Connected: po69u1hn4b8 INFO: 127.0.0.1:49761 - "POST /queue/join HTTP/1.1" 500 Internal Server Error Exception in ASGI application Traceback (most recent call last): File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic\type_adapter.py", line 210, in init core_schema = _getattr_no_parents(type, 'pydantic_core_schema') ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic\type_adapter.py", line 98, in _getattr_no_parents raise AttributeError(attribute) AttributeError: pydantic_core_schema

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\uvicorn\protocols\http\httptools_impl.py", line 401, in run_asgi result = await app( # type: ignore[func-returns-value] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\uvicorn\middleware\proxy_headers.py", line 70, in call return await self.app(scope, receive, send) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi\applications.py", line 1054, in call await super().call(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\applications.py", line 113, in call await self.middleware_stack(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\middleware\errors.py", line 187, in call raise exc File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\middleware\errors.py", line 165, in call await self.app(scope, receive, _send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\gradio\route_utils.py", line 695, in call await self.simple_response(scope, receive, send, request_headers=headers) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\gradio\route_utils.py", line 711, in simple_response await self.app(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\middleware\exceptions.py", line 62, in call await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette_exception_handler.py", line 62, in wrapped_app raise exc File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette_exception_handler.py", line 51, in wrapped_app await app(scope, receive, sender) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\routing.py", line 715, in call await self.middleware_stack(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\routing.py", line 735, in app await route.handle(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\routing.py", line 288, in handle await self.app(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\routing.py", line 76, in app await wrap_app_handling_exceptions(app, request)(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette_exception_handler.py", line 62, in wrapped_app raise exc File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette_exception_handler.py", line 51, in wrapped_app await app(scope, receive, sender) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\routing.py", line 73, in app response = await f(request) ^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi\routing.py", line 291, in app solved_result = await solve_dependencies( ^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi\dependencies\utils.py", line 639, in solve_dependencies ) = await request_body_to_args( # body_params checked above ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi\dependencies\utils.py", line 813, in request_body_to_args fields_to_extract = get_model_fields(firstfield.type) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi_compat.py", line 284, in get_model_fields ModelField(field_info=field_info, name=name) File "", line 6, in init File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi_compat.py", line 109, in post_init__ self._type_adapter: TypeAdapter[Any] = TypeAdapter( ^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic\type_adapter.py", line 212, in init core_schema = _get_schema(type, config_wrapper, parent_depth=_parent_depth + 1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic\type_adapter.py", line 81, in _get_schema schema = gen.generateschema(type) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 499, in generate_schema schema = self._generate_schema_inner(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 734, in _generate_schema_inner return self._annotated_schema(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1749, in _annotated_schema schema = self._apply_annotations(source_type, annotations) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1817, in _apply_annotations schema = get_inner_schema(source_type) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_schema_generation_shared.py", line 82, in call schema = self._handler(source_type) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1899, in new_handler schema = metadata_get_schema(source, get_inner_schema) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1895, in lambda source, handler: handler(source) ^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_schema_generation_shared.py", line 82, in call schema = self._handler(source_type) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1798, in inner_handler schema = self._generate_schema_inner(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 755, in _generate_schema_inner return self.match_type(obj) ^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 837, in match_type return self._match_generic_type(obj, origin) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 861, in _match_generic_type return self._union_schema(obj) ^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1149, in _union_schema choices.append(self.generate_schema(arg)) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 499, in generate_schema schema = self._generate_schema_inner(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 755, in _generate_schema_inner return self.match_type(obj) ^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 841, in match_type return self._unknown_type_schema(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 402, in _unknown_type_schema raise PydanticSchemaGenerationError( pydantic.errors.PydanticSchemaGenerationError: Unable to generate pydantic-core schema for <class 'starlette.requests.Request'>. Set arbitrary_types_allowed=True in the model_config to ignore this error or implement `__get_pydantic_core_schema` on your type to fully support it.

If you got this error by calling handler() within __get_pydantic_core_schema__ then you likely need to call handler.generate_schema(<some type>) since we do not call __get_pydantic_core_schema__ on <some type> otherwise to avoid infinite recursion.

For further information visit https://errors.pydantic.dev/2.7/u/schema-for-unknown-type INFO: 127.0.0.1:49763 - "POST /queue/join HTTP/1.1" 500 Internal Server Error Exception in ASGI application Traceback (most recent call last): File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic\type_adapter.py", line 210, in init core_schema = _getattr_no_parents(type, 'pydantic_core_schema') ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic\type_adapter.py", line 98, in _getattr_no_parents raise AttributeError(attribute) AttributeError: pydantic_core_schema

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\uvicorn\protocols\http\httptools_impl.py", line 401, in run_asgi result = await app( # type: ignore[func-returns-value] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\uvicorn\middleware\proxy_headers.py", line 70, in call return await self.app(scope, receive, send) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi\applications.py", line 1054, in call await super().call(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\applications.py", line 113, in call await self.middleware_stack(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\middleware\errors.py", line 187, in call raise exc File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\middleware\errors.py", line 165, in call await self.app(scope, receive, _send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\gradio\route_utils.py", line 695, in call await self.simple_response(scope, receive, send, request_headers=headers) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\gradio\route_utils.py", line 711, in simple_response await self.app(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\middleware\exceptions.py", line 62, in call await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette_exception_handler.py", line 62, in wrapped_app raise exc File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette_exception_handler.py", line 51, in wrapped_app await app(scope, receive, sender) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\routing.py", line 715, in call await self.middleware_stack(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\routing.py", line 735, in app await route.handle(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\routing.py", line 288, in handle await self.app(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\routing.py", line 76, in app await wrap_app_handling_exceptions(app, request)(scope, receive, send) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette_exception_handler.py", line 62, in wrapped_app raise exc File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette_exception_handler.py", line 51, in wrapped_app await app(scope, receive, sender) File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\starlette\routing.py", line 73, in app response = await f(request) ^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi\routing.py", line 291, in app solved_result = await solve_dependencies( ^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi\dependencies\utils.py", line 639, in solve_dependencies ) = await request_body_to_args( # body_params checked above ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi\dependencies\utils.py", line 813, in request_body_to_args fields_to_extract = get_model_fields(firstfield.type) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi_compat.py", line 284, in get_model_fields ModelField(field_info=field_info, name=name) File "", line 6, in init File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\fastapi_compat.py", line 109, in post_init__ self._type_adapter: TypeAdapter[Any] = TypeAdapter( ^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic\type_adapter.py", line 212, in init core_schema = _get_schema(type, config_wrapper, parent_depth=_parent_depth + 1) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic\type_adapter.py", line 81, in _get_schema schema = gen.generateschema(type) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 499, in generate_schema schema = self._generate_schema_inner(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 734, in _generate_schema_inner return self._annotated_schema(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1749, in _annotated_schema schema = self._apply_annotations(source_type, annotations) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1817, in _apply_annotations schema = get_inner_schema(source_type) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_schema_generation_shared.py", line 82, in call schema = self._handler(source_type) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1899, in new_handler schema = metadata_get_schema(source, get_inner_schema) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1895, in lambda source, handler: handler(source) ^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_schema_generation_shared.py", line 82, in call schema = self._handler(source_type) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1798, in inner_handler schema = self._generate_schema_inner(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 755, in _generate_schema_inner return self.match_type(obj) ^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 837, in match_type return self._match_generic_type(obj, origin) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 861, in _match_generic_type return self._union_schema(obj) ^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 1149, in _union_schema choices.append(self.generate_schema(arg)) ^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 499, in generate_schema schema = self._generate_schema_inner(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 755, in _generate_schema_inner return self.match_type(obj) ^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 841, in match_type return self._unknown_type_schema(obj) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\ProgramData\miniconda3\envs\h2ogpt\Lib\site-packages\pydantic_internal_generate_schema.py", line 402, in _unknown_type_schema raise PydanticSchemaGenerationError( pydantic.errors.PydanticSchemaGenerationError: Unable to generate pydantic-core schema for <class 'starlette.requests.Request'>. Set arbitrary_types_allowed=True in the model_config to ignore this error or implement `__get_pydantic_core_schema` on your type to fully support it.

If you got this error by calling handler() within __get_pydantic_core_schema__ then you likely need to call handler.generate_schema(<some type>) since we do not call __get_pydantic_core_schema__ on <some type> otherwise to avoid infinite recursion.

For further information visit https://errors.pydantic.dev/2.7/u/schema-for-unknown-type

pseudotensor commented 1 month ago

Sounds like the installation is messed up. How did you install? Did you use the predefined script in a clean env?

DrNokkel commented 1 month ago

Yes i followed step by step the windows installation. After that i tried to fix it myself . I will try a new installation.

DrNokkel commented 1 month ago

(h2ogpt) C:\Windows\System32\h2ogpt>python generate.py --share=False --gradio_offline_level=1 --base_model=h2oai/h2ogpt-4096-llama2-7b-chat --score_model=None --prompt_type=human_bot --load_8bit=True Fontconfig error: Cannot load default config file: No such file: (null) C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\pydub\utils.py:170: RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning) No GPUs detected Using Model h2oai/h2ogpt-4096-llama2-7b-chat WARNING:langchain_community.utils.user_agent:USER_AGENT environment variable not set, consider setting it to identify your requests. C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\langchain_core_api\deprecation.py:139: LangChainDeprecationWarning: The class HuggingFaceEmbeddings was deprecated in LangChain 0.2.2 and will be removed in 0.3.0. An updated version of the class exists in the langchain-huggingface package and should be used instead. To use it run pip install -U langchain-huggingface and import as from langchain_huggingface import HuggingFaceEmbeddings. warn_deprecated( Traceback (most recent call last): File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\transformers\utils\import_utils.py", line 1603, in _get_module return importlib.import_module("." + module_name, self.name) File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\importlib__init.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "", line 1050, in _gcd_import File "", line 1027, in _find_and_load File "", line 1006, in _find_and_load_unlocked File "", line 688, in _load_unlocked File "", line 883, in exec_module File "", line 241, in _call_with_frames_removed File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\transformers\trainer.py", line 215, in from peft import PeftModel File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\peft__init__.py", line 22, in from .auto import ( File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\peft\auto.py", line 32, in from .mapping import MODEL_TYPE_TO_PEFT_MODEL_MAPPING File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\peft\mapping.py", line 22, in from peft.tuners.xlora.model import XLoraModel File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\peft\tuners\init.py", line 21, in from .lora import LoraConfig, LoraModel, LoftQConfig, LoraRuntimeConfig File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\peft\tuners\lora\init.py", line 20, in from .model import LoraModel File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\peft\tuners\lora\model.py", line 50, in from .awq import dispatch_awq File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\peft\tuners\lora\awq.py", line 26, in from awq.modules.linear import WQLinear_GEMM File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\awq\init.py", line 2, in from awq.models.auto import AutoAWQForCausalLM File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\awq\models\init__.py", line 1, in from .mpt import MptAWQForCausalLM File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\awq\models\mpt.py", line 1, in from .base import BaseAWQForCausalLM File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\awq\models\base.py", line 16, in from awq.modules.linear import WQLinear_GEMM, WQLinear_GEMV File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\awq\modules\linear.py", line 4, in import awq_inference_engine # with CUDA kernels ImportError: DLL load failed while importing awq_inference_engine: The specified module could not be found.

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "C:\Windows\System32\h2ogpt\generate.py", line 20, in entrypoint_main() File "C:\Windows\System32\h2ogpt\generate.py", line 16, in entrypoint_main H2O_Fire(main) File "C:\Windows\System32\h2ogpt\src\utils.py", line 78, in H2O_Fire fire.Fire(component=component, command=args) File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\fire\core.py", line 143, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\fire\core.py", line 477, in _Fire component, remaining_args = _CallAndUpdateTrace( File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\fire\core.py", line 693, in _CallAndUpdateTrace component = fn(*varargs, *kwargs) File "C:\Windows\System32\h2ogpt\src\gen.py", line 2044, in main model=get_embedding(use_openai_embedding, hf_embedding_model=hf_embedding_model, File "C:\Windows\System32\h2ogpt\src\gpt_langchain.py", line 562, in get_embedding embedding = HuggingFaceEmbeddings(model_name=hf_embedding_model, model_kwargs=model_kwargs) File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\langchain_core_api\deprecation.py", line 203, in warn_if_direct_instance return wrapped(self, args, **kwargs) File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\langchain_community\embeddings\huggingface.py", line 71, in init import sentence_transformers File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\sentence_transformers__init.py", line 15, in from sentence_transformers.trainer import SentenceTransformerTrainer File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\sentence_transformers\trainer.py", line 10, in from transformers import EvalPrediction, PreTrainedTokenizerBase, Trainer, TrainerCallback File "", line 1075, in _handle_fromlist File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\transformers\utils\import_utils.py", line 1593, in getattr__ module = self._get_module(self._class_to_module[name]) File "C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\transformers\utils\import_utils.py", line 1605, in _get_module raise RuntimeError( RuntimeError: Failed to import transformers.trainer because of the following error (look up to see its traceback): DLL load failed while importing awq_inference_engine: The specified module could not be found.

After a fresh installation i got this error. Last time i tried to fix it by myself until the Webinterface errors

pseudotensor commented 1 month ago

For the awq issue, does this help if you install this?

pip install autoawq-kernels -c reqs_optional/reqs_constraints.txt

In your original post, I'm guessing that you were further along, but things failed during use of the UI?

DrNokkel commented 1 month ago

(h2ogpt) C:\Users\thies\h2ogpt>python generate.py --share=False --gradio_offline_level=1 --base_model=h2oai/h2ogpt-4096-llama2-7b-chat --score_model=None --prompt_type=human_bot --load_8bit=True Fontconfig error: Cannot load default config file: No such file: (null) C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\pydub\utils.py:170: RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning) No GPUs detected soundfile, librosa, and wavio not installed, disabling STT soundfile, librosa, and wavio not installed, disabling TTS Using Model h2oai/h2ogpt-4096-llama2-7b-chat USER_AGENT environment variable not set, consider setting it to identify your requests. C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\langchain_core_api\deprecation.py:139: LangChainDeprecationWarning: The class HuggingFaceEmbeddings was deprecated in LangChain 0.2.2 and will be removed in 0.3.0. An updated version of the class exists in the langchain-huggingface package and should be used instead. To use it run pip install -U langchain-huggingface and import as from langchain_huggingface import HuggingFaceEmbeddings. warn_deprecated( C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\transformers\tokenization_utils_base.py:1601: FutureWarning: clean_up_tokenization_spaces was not set. It will be set to True by default. This behavior will be depracted in transformers v4.45, and will be then set to False by default. For more details check this issue: https://github.com/huggingface/transformers/issues/31884 warnings.warn( Starting get_model: h2oai/h2ogpt-4096-llama2-7b-chat C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\huggingface_hub\file_download.py:1150: FutureWarning: resume_download is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use force_download=True. warnings.warn( Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████| 2/2 [00:14<00:00, 7.25s/it] Begin auto-detect HF cache text generation models End auto-detect HF cache text generation models Begin auto-detect llama.cpp models End auto-detect llama.cpp models C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\gradio\components\dropdown.py:179: UserWarning: The value passed into gr.Dropdown() is not in the list of choices. Please update the list of choices to include: None or set allow_custom_value=True. warnings.warn( Running on local URL: http://0.0.0.0:7860

To create a public link, set share=True in launch(). Started Gradio Server and/or GUI: server_name: localhost port: None Use local URL: http://localhost:7860/ C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\pydantic_internal_fields.py:160: UserWarning: Field "modellock" has conflict with protected namespace "model".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = (). warnings.warn( C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\pydantic_internal_fields.py:160: UserWarning: Field "modelinfo" has conflict with protected namespace "model".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = (). warnings.warn( C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\pydantic_internal_fields.py:160: UserWarning: Field "modelnames" has conflict with protected namespace "model".

You may be able to resolve this warning by setting model_config['protected_namespaces'] = (). warnings.warn( verbose disabled OpenAI API URL: http://0.0.0.0:5000 OpenAI API key: EMPTY INFO: 127.0.0.1:51867 - "GET / HTTP/1.1" 200 OK INFO: 127.0.0.1:51867 - "GET /info HTTP/1.1" 200 OK INFO: 127.0.0.1:51867 - "GET /favicon.ico HTTP/1.1" 200 OK INFO: 127.0.0.1:51867 - "GET /theme.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51867 - "GET /heartbeat/rz68hpe3k2k HTTP/1.1" 200 OK Client Connected: rz68hpe3k2k INFO: 127.0.0.1:51875 - "GET / HTTP/1.1" 200 OK Client disconnected: rz68hpe3k2k INFO: 127.0.0.1:51875 - "GET /info HTTP/1.1" 200 OK INFO: 127.0.0.1:51875 - "GET /theme.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51876 - "GET /heartbeat/ec6wxy0tk2o HTTP/1.1" 200 OK Client Connected: ec6wxy0tk2o INFO: 127.0.0.1:51888 - "GET / HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /assets/index-380480d1.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /assets/index-4ea145fa.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /assets/svelte/svelte.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /assets/Index-3a0c450d.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /assets/Index-c88eb5f1.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /info HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /theme.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /assets/SelectSource-ffeae268.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /assets/Blocks-a37e4ec0.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /assets/Blocks-c34a3b8c.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /assets/SelectSource.svelte_svelte_type_style_lang-adcf3c44.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51888 - "GET /heartbeat/91e1jxkuq56 HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/api-logo-5346f193.svg HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/logo-3707f936.svg HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-79eb3848.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Example-09c7df8b.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-edf307d2.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-93c91554.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-2853eb31.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-8f1feca1.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Example-98fc2b2c.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-7f696158.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-7a433ab1.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-76c3ee3f.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-3812b7f1.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Textbox-dde6f8cc.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Example-6ded08d8.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/ModifyUpload-13b13e32.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/FileUpload-a4fc0425.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Example-1cda6415.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-51c40da3.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Image-c2f962bb.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/ImageUploader-b33972d3.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Example-bcfbe567.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Video-a80c372b.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Example-9429a5cb.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/index-5522f595.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Tabs-a57f85ff.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-d43fcb36.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-329f8260.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-efd1eb27.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Index-8af74d56.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Example-da1a7264.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Index-83656a6f.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-b658ebcd.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /custom_component/98a833ceec073ac17ed81e096eb6a8cf/component/style.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/index-da1c5d77.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Index-8f24ac6d.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-8c6a6015.css HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Index-a00e552c.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index.svelte_svelte_type_style_lang-0afb02c2.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/utils-572af92b.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Example.svelte_svelte_type_style_lang-2c410615.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/prism-python-73fafd54.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-b2fbe4c6.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Example-b7e49832.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Index-2ea49b90.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-2d00126c.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Index-b88bd069.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-667acb08.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/BlockTitle-341cd4bd.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Info-9c6ce410.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Index-4519e1de.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Example-36c18249.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/DropdownArrow-c1184342.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Example-e7bf77ec.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Index-4d98cf33.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-46e5737c.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Index-073ecbe4.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Textbox-105527d7.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Check-965babbe.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Copy-b365948f.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Example-d6a316ec.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-3bc00d54.js HTTP/1.1" 200 OK Client Connected: 91e1jxkuq56 INFO: 127.0.0.1:51903 - "GET /assets/FileUpload-45ee7e35.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Empty-e94c8b62.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/BlockLabel-2524f0c6.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/File-d0b52941.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/ModifyUpload-75c48d83.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/ModifyUpload.svelte_svelte_type_style_lang-5d7cfa29.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/IconButton-98904c3d.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/DownloadLink-2061f7f7.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Clear-2c7bae91.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/file-url-65353b28.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Undo-b088de14.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/UploadText-b6444409.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Upload-351cc897.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Example-e82c91a3.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Index-36d4562e.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/ImageUploader-f5fe978e.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-693f6e84.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/ShareButton-b22e3a12.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Image-eaba773f.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Image-c454d182.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/SelectSource-b0a5278e.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Example-487e4071.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/index-d5419efa.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Video-99f28ea4.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Video-8670328f.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Trim-1b343e72.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Example-490940c1.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-2d295f17.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Tabs-33cd00ce.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Index-2d3c42f0.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-be7c0f16.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Index-36d2ae00.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/Index-36a0cae0.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/index-2f00b72c.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Index-5edcd718.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /assets/dsv-576afacd.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Example-4e86bea7.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Index-0c1d215c.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/index-c455d978.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51902 - "GET /custom_component/98a833ceec073ac17ed81e096eb6a8cf/component/index.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Music-755043aa.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Example-8632de63.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51903 - "GET /assets/Index-aa84147a.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /assets/Index-73a5f22f.js HTTP/1.1" 200 OK INFO: 127.0.0.1:51901 - "GET /favicon.ico HTTP/1.1" 200 OK Client disconnected: ec6wxy0tk2o

It started now but these parts looking nit right for me

Fontconfig error: Cannot load default config file: No such file: (null) C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\pydub\utils.py:170: RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning) No GPUs detected soundfile, librosa, and wavio not installed, disabling STT soundfile, librosa, and wavio not installed, disabling TTS

I have an GPU installed +-----------------------------------------------------------------------------------------+ | NVIDIA-SMI 552.23 Driver Version: 552.23 CUDA Version: 12.4 | |-----------------------------------------+------------------------+----------------------+ | GPU Name TCC/WDDM | Bus-Id Disp.A | Volatile Uncorr. ECC | | Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. | | | | MIG M. | |=========================================+========================+======================| | 0 NVIDIA RTX 2000 Ada Gene... WDDM | 00000000:01:00.0 On | Off | | 30% 26C P8 4W / 70W | 349MiB / 16380MiB | 2% Default | | | | N/A | +-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+ | Processes: | | GPU GI CI PID Type Process name GPU Memory | | ID ID Usage | |=========================================================================================| | 0 N/A N/A 2716 C+G ...5n1h2txyewy\ShellExperienceHost.exe N/A | | 0 N/A N/A 5212 C+G ..._8wekyb3d8bbwe\Microsoft.Photos.exe N/A | | 0 N/A N/A 6880 C+G ...siveControlPanel\SystemSettings.exe N/A | | 0 N/A N/A 7036 C+G C:\Windows\explorer.exe N/A | | 0 N/A N/A 7656 C+G ...nt.CBS_cw5n1h2txyewy\SearchHost.exe N/A | | 0 N/A N/A 7680 C+G ...2txyewy\StartMenuExperienceHost.exe N/A | | 0 N/A N/A 9848 C+G ...on\128.0.2739.67\msedgewebview2.exe N/A | | 0 N/A N/A 9948 C+G ...crosoft\Edge\Application\msedge.exe N/A | +-----------------------------------------------------------------------------------------+

I can open the localhost link. But its stuck in this screen image

pseudotensor commented 1 month ago

Interesting on the stuck screen. Same as https://github.com/h2oai/h2ogpt/issues/1834

DrNokkel commented 1 month ago

For the awq issue, does this help if you install this?

pip install autoawq-kernels -c reqs_optional/reqs_constraints.txt

In your original post, I'm guessing that you were further along, but things failed during use of the UI?

Yes i couldnt press anything in the ui , everytime I pressed a button more error messages popping up

DrNokkel commented 1 month ago

Interesting on the stuck screen. Same as #1834 Thanks for the support ill try it this way

pseudotensor commented 1 month ago

Could you try doing:

pip uninstall gradio gradio_client -y
pip install gradio==3.50.2 # also installs client

and see if anything changed?

DrNokkel commented 1 month ago

Yes its helping thanks

DrNokkel commented 1 month ago

Its just a bit slow. I think ive got another problem with no gpu detecting.

But really nice support here

pseudotensor commented 1 month ago

I recommend using GGUF of some modern model. The h2oai/h2ogpt-4096-llama2-7b-chat you chose is super old and without GGUF requires beefier GPU.

DrNokkel commented 1 month ago

Okay thanks.

(h2ogpt) C:\Windows\System32\h2ogpt>python generate.py --share=False --gradio_offline_level=1 --base_model=h2oai/h2ogpt-4096-llama2-7b-chat --score_model=None --prompt_type=human_bot --load_8bit=True Fontconfig error: Cannot load default config file: No such file: (null) C:\ProgramData\miniconda3\envs\h2ogpt\lib\site-packages\pydub\utils.py:170: RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning) No GPUs detected

Im just suprised why theres no gpu detected

DrNokkel commented 3 weeks ago

Getting this now

(h2ogpt2) C:\Windows\System32\h2ogpt>python generate.py --share=False --gradio_offline_level=1 --base_model=h2oai/h2ogpt-4096-llama2-7b-chat --score_model=None --prompt_type=human_bot --load_8bit=True Fontconfig error: Cannot load default config file: No such file: (null) C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\pydub\utils.py:170: RuntimeWarning: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work warn("Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work", RuntimeWarning) Using Model h2oai/h2ogpt-4096-llama2-7b-chat WARNING:langchain_community.utils.user_agent:USER_AGENT environment variable not set, consider setting it to identify your requests. Windows fatal exception: code 0xc0000139

Current thread 0x00001e14 (most recent call first): File "", line 241 in _call_with_frames_removed File "", line 1176 in create_module File "", line 571 in module_from_spec File "", line 674 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\awq\modules\linear.py", line 4 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\awq\models\base.py", line 16 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\awq\models\mpt.py", line 1 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\awq\models__init.py", line 1 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "", line 241 in _call_with_frames_removed File "", line 992 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\awq__init.py", line 2 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "", line 241 in _call_with_frames_removed File "", line 992 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "", line 241 in _call_with_frames_removed File "", line 992 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\tuners\lora\awq.py", line 26 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\tuners\lora\model.py", line 50 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\tuners\lora__init.py", line 20 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\tuners\init.py", line 21 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "", line 241 in _call_with_frames_removed File "", line 992 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "", line 241 in _call_with_frames_removed File "", line 992 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\mapping.py", line 22 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\auto.py", line 32 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\init.py", line 22 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\transformers\trainer.py", line 215 in File "", line 241 in _call_with_frames_removed File "", line 883 in exec_module File "", line 688 in _load_unlocked File "", line 1006 in _find_and_load_unlocked File "", line 1027 in _find_and_load File "", line 1050 in _gcd_import ... Traceback (most recent call last): File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\transformers\utils\import_utils.py", line 1603, in _get_module return importlib.import_module("." + module_name, self.name) File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\importlib\init__.py", line 126, in import_module return _bootstrap._gcd_import(name[level:], package, level) File "", line 1050, in _gcd_import File "", line 1027, in _find_and_load File "", line 1006, in _find_and_load_unlocked File "", line 688, in _load_unlocked File "", line 883, in exec_module File "", line 241, in _call_with_frames_removed File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\transformers\trainer.py", line 215, in from peft import PeftModel File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\init__.py", line 22, in from .auto import ( File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\auto.py", line 32, in from .mapping import MODEL_TYPE_TO_PEFT_MODEL_MAPPING File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\mapping.py", line 22, in from peft.tuners.xlora.model import XLoraModel File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\tuners\init.py", line 21, in from .lora import LoraConfig, LoraModel, LoftQConfig, LoraRuntimeConfig File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\tuners\lora\init.py", line 20, in from .model import LoraModel File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\tuners\lora\model.py", line 50, in from .awq import dispatch_awq File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\peft\tuners\lora\awq.py", line 26, in from awq.modules.linear import WQLinear_GEMM File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\awq\init.py", line 2, in from awq.models.auto import AutoAWQForCausalLM File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\awq\models\init__.py", line 1, in from .mpt import MptAWQForCausalLM File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\awq\models\mpt.py", line 1, in from .base import BaseAWQForCausalLM File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\awq\models\base.py", line 16, in from awq.modules.linear import WQLinear_GEMM, WQLinear_GEMV File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\awq\modules\linear.py", line 4, in import awq_inference_engine # with CUDA kernels ImportError: DLL load failed while importing awq_inference_engine: The specified procedure could not be found.

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "C:\Windows\System32\h2ogpt\generate.py", line 20, in entrypoint_main() File "C:\Windows\System32\h2ogpt\generate.py", line 16, in entrypoint_main H2O_Fire(main) File "C:\Windows\System32\h2ogpt\src\utils.py", line 79, in H2O_Fire fire.Fire(component=component, command=args) File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\fire\core.py", line 143, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\fire\core.py", line 477, in _Fire component, remaining_args = _CallAndUpdateTrace( File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\fire\core.py", line 693, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) File "C:\Windows\System32\h2ogpt\src\gen.py", line 2044, in main model=get_embedding(use_openai_embedding, hf_embedding_model=hf_embedding_model, File "C:\Windows\System32\h2ogpt\src\gpt_langchain.py", line 550, in get_embedding embedding = HuggingFaceBgeEmbeddings(model_name=hf_embedding_model, File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\langchain_community\embeddings\huggingface.py", line 287, in init import sentence_transformers File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\sentence_transformers__init.py", line 17, in from sentence_transformers.trainer import SentenceTransformerTrainer File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\sentence_transformers\trainer.py", line 13, in from transformers import EvalPrediction, PreTrainedTokenizerBase, Trainer, TrainerCallback File "", line 1075, in _handle_fromlist File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\transformers\utils\import_utils.py", line 1593, in getattr__ module = self._get_module(self._class_to_module[name]) File "C:\Users\das\miniconda3\envs\h2ogpt2\lib\site-packages\transformers\utils\import_utils.py", line 1605, in _get_module raise RuntimeError( RuntimeError: Failed to import transformers.trainer because of the following error (look up to see its traceback): DLL load failed while importing awq_inference_engine: The specified procedure could not be found.

I try this but it doesn't helped

For the awq issue, does this help if you install this?

pip install autoawq-kernels -c reqs_optional/reqs_constraints.txt

In your original post, I'm guessing that you were further along, but things failed during use of the UI?

Anything what im doing wrong?

pseudotensor commented 3 weeks ago

I'm unsure, seems like peft needs awq and that fails on your system. I would avoid 8bit loading and just use GGUF.

pseudotensor commented 2 weeks ago

The gradio pydantic thing is fixed: https://github.com/h2oai/h2ogpt/commit/be5f37ef283ebd4321bc5f40980accf5d9822e6c