如何传本地的模型路径？

[cqray1990]

if model_name.startswith("hosted_vllm/") and (
    "localhost" in host or host == "0.0.0.0" or host == "127.0.0.1"
):

源代码都有这个判断，hosted_vllm 只是文件夹的名字吧，这样判断是不是太绝对了？，直接传路径下面报错

litellm.exceptions.BadRequestError: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=/QWEN2/Qwen2.5-VL-7B-Instruct-AWQ
Pass model as E.g. For 'Huggingface' inference endpoints pass in `completion(model='huggingface/starcoder',..)

[github-actions]

👋 Welcome! Thanks for opening your first issue. If you'd like to take a crack at fixing it, feel free to open a pull request — otherwise, we'll take a look as soon as we can!

[mandalsouvik3333]

You can pass this as --model hosted_vllm//QWEN2/Qwen2.5-VL-7B-Instruct-AWQ, if your model is saved at /QWEN2/Qwen2.5-VL-7B-Instruct-AWQ

[kkiskkk]

You can pass this as --model hosted_vllm//QWEN2/Qwen2.5-VL-7B-Instruct-AWQ, if your model is saved at /QWEN2/Qwen2.5-VL-7B-Instruct-AWQ如果您的模型保存在 /QWEN2/Qwen2.5-VL-7B-Instruct-AWQ

也就是说--model_name hosted_vllm//path/Qwen2.5-VL-7B-Instruct 是吗？ 但是我还是会报错
ERROR 07-22 20:27:59 [core.py:390] File "/app/.venv/lib/python3.11/site-packages/vllm/transformers_utils/processor.py", line 127, in get_image_processor
ERROR 07-22 20:27:59 [core.py:390] processor = AutoImageProcessor.from_pretrained(
ERROR 07-22 20:27:59 [core.py:390] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
ERROR 07-22 20:27:59 [core.py:390] File "/app/.venv/lib/python3.11/site-packages/transformers/models/auto/image_processing_auto.py", line 579, in from_pretrained
ERROR 07-22 20:27:59 [core.py:390] raise ValueError(
ERROR 07-22 20:27:59 [core.py:390] ValueError: Unrecognized image processor in /cpfs/data/user/docext/QWEN2/Qwen2.5-VL-7B-Instruct.