参考页面：https://www.hiascend.com/developer/ascendhub/detail/mis-tei

权重所在路径：/data/0310/bge-m3
映射到容器里面pwd显示路径：/home/HwHiAiUser/model

docker run -e -itd --name=tei --net=host -v /data/0310/bge-m3:/home/HwHiAiUser/model swr.cn-south-1.myhuaweicloud.com/ascendhub/mis-tei:6.0.0-300I-Duo-aarch64 BAAI/bge-m3 192.168.137.135 8111

有一点不理解的地方为文字加粗部分写的是否正确(下载模型链接为：https://huggingface.co/BAAI/bge-m3)

具体报错信息如下：

[root@bogon ~]# docker logs tei

Model 'bge-m3' exists.

NPU_ID: 32896, CHIP_ID: 0， CHIP_LOGIC_ID: 0 CHIP_TYPE: 310P3, MEMORY_TYPE: DDR, CAPACITY: 43693, USAGE_RATE: 3, AVAIL_CAPACITY: 42382

Using NPU: 0 start TEI service

Starting TEI service on 192.168.137.135:8111...

2025-03-11T14:29:06.389322Z  INFO text_embeddings_router: router/src/main.rs:140: Args { model_id: "/hom*/**********/*****/**e-m3", revision: None, tokenization_workers: None, dtype: None, pooling: None, max_concurrent_requests: 512, max_batch_tokens: 16384, max_batch_requests: None, max_client_batch_size: 32, auto_truncate: false, hf_api_token: None, hostname: "192.168.137.135", port: 8111, uds_path: "/tmp/text-embeddings-inference-server", huggingface_hub_cache: None, payload_limit: 2000000, api_key: None, json_output: false, otlp_endpoint: None, cors_allow_origin: None }

2025-03-11T14:29:06.790580Z  INFO text_embeddings_router: router/src/lib.rs:169: Maximum number of tokens per request: 8192

2025-03-11T14:29:06.791315Z  INFO text_embeddings_core::tokenization: core/src/tokenization.rs:23: Starting 128 tokenization workers

2025-03-11T14:29:27.921081Z  INFO text_embeddings_router: router/src/lib.rs:198: Starting model backend

2025-03-11T14:29:27.921414Z  INFO text_embeddings_backend_python::management: backends/python/src/management.rs:62: Starting Python backend

2025-03-11T14:29:31.773656Z  WARN python-backend: text_embeddings_backend_python::logging: backends/python/src/logging.rs:39: Could not import Flash Attention enabled models: No module named 'dropout_layer_norm'

2025-03-11T14:29:38.018563Z  INFO text_embeddings_backend_python::management: backends/python/src/management.rs:126: Waiting for Python backend to be ready...

2025-03-11T14:29:40.520215Z ERROR python-backend: text_embeddings_backend_python::logging: backends/python/src/logging.rs:40: Error when initializing model

Traceback (most recent call last):

  File "/home/HwHiAiUser/.local/bin/python-text-embeddings-server", line 8, in <module>

    sys.exit(app())

  File "/home/HwHiAiUser/.local/lib/python3.11/site-packages/typer/main.py", line 311, in __call__

    return get_command(self)(*args, **kwargs)

  File "/home/HwHiAiUser/.local/lib/python3.11/site-packages/click/core.py", line 1157, in __call__

    return self.main(*args, **kwargs)

  File "/home/HwHiAiUser/.local/lib/python3.11/site-packages/typer/core.py", line 716, in main

    return _main(

  File "/home/HwHiAiUser/.local/lib/python3.11/site-packages/typer/core.py", line 216, in _main

    rv = self.invoke(ctx)

  File "/home/HwHiAiUser/.local/lib/python3.11/site-packages/click/core.py", line 1434, in invoke

    return ctx.invoke(self.callback, **ctx.params)

  File "/home/HwHiAiUser/.local/lib/python3.11/site-packages/click/core.py", line 783, in invoke

    return __callback(*args, **kwargs)

  File "/home/HwHiAiUser/.local/lib/python3.11/site-packages/typer/main.py", line 683, in wrapper

    return callback(**use_params)  # type: ignore

  File "/home/HwHiAiUser/text-embeddings-inference/backends/python/server/text_embeddings_server/cli.py", line 51, in serve

    server.serve(model_path, dtype, uds_path, pool)

  File "/home/HwHiAiUser/text-embeddings-inference/backends/python/server/text_embeddings_server/server.py", line 94, in serve

    asyncio.run(serve_inner(model_path, dtype))

  File "/usr/lib/python3.11/asyncio/runners.py", line 190, in run

    return runner.run(main)

  File "/usr/lib/python3.11/asyncio/runners.py", line 118, in run

    return self._loop.run_until_complete(task)

  File "/usr/lib/python3.11/asyncio/base_events.py", line 641, in run_until_complete

    self.run_forever()

  File "/usr/lib/python3.11/asyncio/base_events.py", line 608, in run_forever

    self._run_once()

  File "/usr/lib/python3.11/asyncio/base_events.py", line 1936, in _run_once

    handle._run()

  File "/usr/lib/python3.11/asyncio/events.py", line 84, in _run

    self._context.run(self._callback, *self._args)

> File "/home/HwHiAiUser/text-embeddings-inference/backends/python/server/text_embeddings_server/server.py", line 63, in serve_inner

    model = get_model(model_path, dtype, pool)

  File "/home/HwHiAiUser/text-embeddings-inference/backends/python/server/text_embeddings_server/models/__init__.py", line 83, in get_model

    return DefaultModel(model_path, device, dtype, pool)

  File "/home/HwHiAiUser/text-embeddings-inference/backends/python/server/text_embeddings_server/models/default_model.py", line 20, in __init__

    model = AutoModel.from_pretrained(model_path).to(dtype).to(device).eval()

  File "/home/HwHiAiUser/.local/lib/python3.11/site-packages/transformers/models/auto/auto_factory.py", line 563, in from_pretrained

    return model_class.from_pretrained(

  File "/home/HwHiAiUser/.local/lib/python3.11/site-packages/transformers/modeling_utils.py", line 3305, in from_pretrained

    raise EnvironmentError(

OSError: Error no file named pytorch_model.bin, model.safetensors, tf_model.h5, model.ckpt.index or flax_model.msgpack found in directory /home/HwHiAiUser/model/bge-m3.

2025-03-11T14:29:48.020359Z  INFO text_embeddings_backend_python::management: backends/python/src/management.rs:126: Waiting for Python backend to be ready...

Error: Could not create backend

Caused by:

    Could not start backend: Python backend failed to start