VILA docker issue

Traceback (most recent call last):
  File "main.py", line 8, in <module>
    response = client.chat.completions.create(
  File "/home/ubuntu/.local/share/virtualenvs/Wesen-HYipQkKz/lib/python3.8/site-packages/openai/_utils/_utils.py", line 279, in wrapper
    return func(*args, **kwargs)
  File "/home/ubuntu/.local/share/virtualenvs/Wesen-HYipQkKz/lib/python3.8/site-packages/openai/resources/chat/completions.py", line 859, in create
    return self._post(
  File "/home/ubuntu/.local/share/virtualenvs/Wesen-HYipQkKz/lib/python3.8/site-packages/openai/_base_client.py", line 1283, in post
    return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
  File "/home/ubuntu/.local/share/virtualenvs/Wesen-HYipQkKz/lib/python3.8/site-packages/openai/_base_client.py", line 960, in request
    return self._request(
  File "/home/ubuntu/.local/share/virtualenvs/Wesen-HYipQkKz/lib/python3.8/site-packages/openai/_base_client.py", line 1064, in _request
    raise self._make_status_error_from_response(err.response) from None
openai.UnprocessableEntityError: Error code: 422 - {'detail': [{'loc': ['body', 'model'], 'msg': "unexpected value; permitted: 'VILA1.5-3B', 'VILA1.5-3B-AWQ', 'VILA1.5-3B-S2', 'VILA1.5-3B-S2-AWQ', 'Llama-3-VILA1.5-8B', 'Llama-3-VILA1.5-8B-AWQ', 'VILA1.5-13B', 'VILA1.5-13B-AWQ', 'VILA1.5-40B', 'VILA1.5-40B-AWQ'", 'type': 'value_error.const', 'ctx': {'given': 'NVILA-15B', 'permitted': ['VILA1.5-3B', 'VILA1.5-3B-AWQ', 'VILA1.5-3B-S2', 'VILA1.5-3B-S2-AWQ', 'Llama-3-VILA1.5-8B', 'Llama-3-VILA1.5-8B-AWQ', 'VILA1.5-13B', 'VILA1.5-13B-AWQ', 'VILA1.5-40B', 'VILA1.5-40B-AWQ']}}]}

VILA, I have clone and build the image from this repo and try to run some example with an image, but an error has shown above.

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:8200",
    api_key="fake-key",
)

response = client.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "What’s in this image?"},
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://blog.logomyway.com/wp-content/uploads/2022/01/NVIDIA-logo.jpg",
                        # Or you can pass in a base64 encoded image
                        # "url": "data:image/png;base64,<base64_encoded_image>",
                    },
                },
            ],
        }
    ],
    model="NVILA-15B",
)

print(response.choices[0].message.content)

This is the python code to run the example.

Hi @wesen.khoo, sorry for the late reply. Could you try to add the NVILA-15B to the list of the server below?
https://github.com/NVlabs/VILA/blob/main/server.py#L53

We have tried same repo for docker image with Vila 15 B.
Docker image is built and running but when we are trying to get response from same running docker image then getting error:

Hi @priya.i.shukla , for the VILA related issues, we recommend that you raise an issue directly to the VILA repo. Thanks

Hi, It is same for NVila 15 B also

Hi @priya.i.shukla , this forum is currently focused on questions related to the Video Search and Summarization Agent, and it is recommended to ask questions about the VILA project directly on the github. Thanks