的笔记本是Win11，未安装dock环境，然后我运行官方的yuanchat.exe程序，弹出页面后载入yuan2-102B这个目录（官方发布的文件，未修改），然后出错了。不知怎么解决 ？
完整的运行日志如下:
2024-03-03 19:52:23,937 - modelscope - INFO - PyTorch version 2.1.1+cpu Found.
2024-03-03 19:52:23,942 - modelscope - INFO - Loading ast index from C:\Users\gxl\.cache\modelscope\ast_indexer
2024-03-03 19:52:23,942 - modelscope - INFO - Loading done! Current index file version is 1.11.1, with md5 d41d8cd98f00b204e9800998ecf8427e and a total number of 0 components indexed
INFO: Started server process [12800]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:5050 (Press CTRL+C to quit)
INFO: 127.0.0.1:53626 - "GET / HTTP/1.1" 200 OK
INFO: 127.0.0.1:53626 - "GET /yuan-chat/assets/index-a6fd3234.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:53627 - "GET /yuan-chat/assets/index-c25d3371.css HTTP/1.1" 200 OK
INFO: 127.0.0.1:53627 - "GET /yuan-chat/assets/Index-18240267.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:53627 - "GET /yuan-chat/assets/_plugin-vue_export-helper-e58a387b.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:53627 - "GET /yuan-chat/assets/Index-ab9351d1.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:53626 - "GET /yuan-chat/assets/_plugin-vue_export-helper-f5c6a819.css HTTP/1.1" 200 OK
INFO: 127.0.0.1:53628 - "GET /yuan-chat/assets/Index-61bf5e8b.css HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/assets/Index-89ead46e.css HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/logo.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/recommends.json HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /model/load/status HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /model/load/status HTTP/1.1" 200 OK
INFO: 127.0.0.1:53628 - "GET /yuan-chat/avatar-yuan.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/avatar-user.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/icons/icon_thumb_up_default.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53628 - "GET /yuan-chat/icons/icon_thumb_down_default.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/icons/icon_thumb_down_active.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53628 - "GET /yuan-chat/assets/KaTeX_Main-Regular-c2342cd8.woff2 HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/assets/KaTeX_Math-Italic-7af58c5e.woff2 HTTP/1.1" 200 OK
Creat tokenizer...
INFO: 127.0.0.1:53631 - "POST /model/load HTTP/1.1" 200 OK
You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565
INFO: 127.0.0.1:53631 - "GET /model/load/status HTTP/1.1" 200 OK
Creat model...
--- Logging error ---
Traceback (most recent call last):
File "run_text_generation_server_hf.py", line 218, in start_inference_server
File "transformers\models\auto\auto_factory.py", line 553, in from_pretrained
model_class = get_class_from_dynamic_module(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 488, in get_class_from_dynamic_module
final_module = get_cached_module_file(
^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 315, in get_cached_module_file
modules_needed = check_imports(resolved_module_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 180, in check_imports
raise ImportError(
ImportError: This modeling file requires the following packages that were not found in your environment: flash_attn. Run `pip install flash_attn`
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "logging\__init__.py", line 1110, in emit
File "logging\__init__.py", line 953, in format
File "logging\__init__.py", line 687, in format
File "logging\__init__.py", line 377, in getMessage
TypeError: not all arguments converted during string formatting
Call stack:
File "threading.py", line 1002, in _bootstrap
File "threading.py", line 1045, in _bootstrap_inner
File "threading.py", line 982, in run
File "run_text_generation_server_hf.py", line 227, in start_inference_server
File "logging\__init__.py", line 1518, in error
File "logging\__init__.py", line 1634, in _log
File "logging\__init__.py", line 1644, in handle
File "logging\__init__.py", line 1706, in callHandlers
File "logging\__init__.py", line 978, in handle
File "logging\__init__.py", line 1118, in emit
Message: 'start_inference_server error, ex is'
Arguments: (ImportError('This modeling file requires the following packages that were not found in your environment: flash_attn. Run `pip install flash_attn`'),)
--- Logging error ---
Traceback (most recent call last):
File "run_text_generation_server_hf.py", line 218, in start_inference_server
File "transformers\models\auto\auto_factory.py", line 553, in from_pretrained
model_class = get_class_from_dynamic_module(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 488, in get_class_from_dynamic_module
final_module = get_cached_module_file(
^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 315, in get_cached_module_file
modules_needed = check_imports(resolved_module_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 180, in check_imports
raise ImportError(
ImportError: This modeling file requires the following packages that were not found in your environment: flash_attn. Run `pip install flash_attn`
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "logging\__init__.py", line 1110, in emit
File "logging\__init__.py", line 953, in format
File "logging\__init__.py", line 687, in format
File "logging\__init__.py", line 377, in getMessage
TypeError: not all arguments converted during string formatting
Call stack:
File "threading.py", line 1002, in _bootstrap
File "threading.py", line 1045, in _bootstrap_inner
File "threading.py", line 982, in run
File "run_text_generation_server_hf.py", line 227, in start_inference_server
File "logging\__init__.py", line 1518, in error
File "logging\__init__.py", line 1634, in _log
File "logging\__init__.py", line 1644, in handle
File "logging\__init__.py", line 1706, in callHandlers
File "logging\__init__.py", line 978, in handle
File "logging\__init__.py", line 1230, in emit
File "logging\__init__.py", line 1118, in emit
Message: 'start_inference_server error, ex is'
Arguments: (ImportError('This modeling file requires the following packages that were not found in your environment: flash_attn. Run `pip install flash_attn`'),)
INFO: 127.0.0.1:53631 - "GET /model/load/status HTTP/1.1" 200 OK
不知怎么解决 ？
完整的运行日志如下:
2024-03-03 19:52:23,937 - modelscope - INFO - PyTorch version 2.1.1+cpu Found.
2024-03-03 19:52:23,942 - modelscope - INFO - Loading ast index from C:\Users\gxl\.cache\modelscope\ast_indexer
2024-03-03 19:52:23,942 - modelscope - INFO - Loading done! Current index file version is 1.11.1, with md5 d41d8cd98f00b204e9800998ecf8427e and a total number of 0 components indexed
INFO: Started server process [12800]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:5050 (Press CTRL+C to quit)
INFO: 127.0.0.1:53626 - "GET / HTTP/1.1" 200 OK
INFO: 127.0.0.1:53626 - "GET /yuan-chat/assets/index-a6fd3234.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:53627 - "GET /yuan-chat/assets/index-c25d3371.css HTTP/1.1" 200 OK
INFO: 127.0.0.1:53627 - "GET /yuan-chat/assets/Index-18240267.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:53627 - "GET /yuan-chat/assets/_plugin-vue_export-helper-e58a387b.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:53627 - "GET /yuan-chat/assets/Index-ab9351d1.js HTTP/1.1" 200 OK
INFO: 127.0.0.1:53626 - "GET /yuan-chat/assets/_plugin-vue_export-helper-f5c6a819.css HTTP/1.1" 200 OK
INFO: 127.0.0.1:53628 - "GET /yuan-chat/assets/Index-61bf5e8b.css HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/assets/Index-89ead46e.css HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/logo.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/recommends.json HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /model/load/status HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /model/load/status HTTP/1.1" 200 OK
INFO: 127.0.0.1:53628 - "GET /yuan-chat/avatar-yuan.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/avatar-user.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/icons/icon_thumb_up_default.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53628 - "GET /yuan-chat/icons/icon_thumb_down_default.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/icons/icon_thumb_down_active.png HTTP/1.1" 200 OK
INFO: 127.0.0.1:53628 - "GET /yuan-chat/assets/KaTeX_Main-Regular-c2342cd8.woff2 HTTP/1.1" 200 OK
INFO: 127.0.0.1:53629 - "GET /yuan-chat/assets/KaTeX_Math-Italic-7af58c5e.woff2 HTTP/1.1" 200 OK
Creat tokenizer...
INFO: 127.0.0.1:53631 - "POST /model/load HTTP/1.1" 200 OK
You are using the default legacy behaviour of the <class 'transformers.models.llama.tokenization_llama.LlamaTokenizer'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thoroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565
INFO: 127.0.0.1:53631 - "GET /model/load/status HTTP/1.1" 200 OK
Creat model...
--- Logging error ---
Traceback (most recent call last):
File "run_text_generation_server_hf.py", line 218, in start_inference_server
File "transformers\models\auto\auto_factory.py", line 553, in from_pretrained
model_class = get_class_from_dynamic_module(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 488, in get_class_from_dynamic_module
final_module = get_cached_module_file(
^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 315, in get_cached_module_file
modules_needed = check_imports(resolved_module_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 180, in check_imports
raise ImportError(
ImportError: This modeling file requires the following packages that were not found in your environment: flash_attn. Run `pip install flash_attn`
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "logging\__init__.py", line 1110, in emit
File "logging\__init__.py", line 953, in format
File "logging\__init__.py", line 687, in format
File "logging\__init__.py", line 377, in getMessage
TypeError: not all arguments converted during string formatting
Call stack:
File "threading.py", line 1002, in _bootstrap
File "threading.py", line 1045, in _bootstrap_inner
File "threading.py", line 982, in run
File "run_text_generation_server_hf.py", line 227, in start_inference_server
File "logging\__init__.py", line 1518, in error
File "logging\__init__.py", line 1634, in _log
File "logging\__init__.py", line 1644, in handle
File "logging\__init__.py", line 1706, in callHandlers
File "logging\__init__.py", line 978, in handle
File "logging\__init__.py", line 1118, in emit
Message: 'start_inference_server error, ex is'
Arguments: (ImportError('This modeling file requires the following packages that were not found in your environment: flash_attn. Run `pip install flash_attn`'),)
--- Logging error ---
Traceback (most recent call last):
File "run_text_generation_server_hf.py", line 218, in start_inference_server
File "transformers\models\auto\auto_factory.py", line 553, in from_pretrained
model_class = get_class_from_dynamic_module(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 488, in get_class_from_dynamic_module
final_module = get_cached_module_file(
^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 315, in get_cached_module_file
modules_needed = check_imports(resolved_module_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "transformers\dynamic_module_utils.py", line 180, in check_imports
raise ImportError(
ImportError: This modeling file requires the following packages that were not found in your environment: flash_attn. Run `pip install flash_attn`
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "logging\__init__.py", line 1110, in emit
File "logging\__init__.py", line 953, in format
File "logging\__init__.py", line 687, in format
File "logging\__init__.py", line 377, in getMessage
TypeError: not all arguments converted during string formatting
Call stack:
File "threading.py", line 1002, in _bootstrap
File "threading.py", line 1045, in _bootstrap_inner
File "threading.py", line 982, in run
File "run_text_generation_server_hf.py", line 227, in start_inference_server
File "logging\__init__.py", line 1518, in error
File "logging\__init__.py", line 1634, in _log
File "logging\__init__.py", line 1644, in handle
File "logging\__init__.py", line 1706, in callHandlers
File "logging\__init__.py", line 978, in handle
File "logging\__init__.py", line 1230, in emit
File "logging\__init__.py", line 1118, in emit
Message: 'start_inference_server error, ex is'
Arguments: (ImportError('This modeling file requires the following packages that were not found in your environment: flash_attn. Run `pip install flash_attn`'),)
INFO: 127.0.0.1:53631 - "GET /model/load/status HTTP/1.1" 200 OK
不知怎么解决 ？
