Unable to depploy this model using vLLM

by hdnh2006 - opened 5 days ago

hdnh2006

5 days ago

Hi, I am just following the suggestion from huggingface and I am running:

vllm serve "bnb-community/Llama-4-Scout-17B-16E-Instruct-bnb-4bit"

Unfortunately I got this error:

ERROR 04-08 07:32:28 [core.py:390] OSError: bnb-community/Llama-4-Scout-17B-16E-Instruct-bnb-4bit does not appear to have a file named preprocessor_config.json. Checkout 'https://huggingface.co/bnb-community/Llama-4-Scout-17B-16E-Instruct-bnb-4bit/tree/main'for available files.

Any idea?

medmekk

Bitsandbytes Community org 5 days ago

thanks for reporting ! Yes I updated the processor files on the repo, I think this should solve the problem

george-arta

4 days ago

got assertion error

ERROR 04-09 13:25:06 [core.py:390]     assert self.quant_method is not None
ERROR 04-09 13:25:06 [core.py:390] AssertionError

medmekk

Bitsandbytes Community org 4 days ago

Hi @george-arta ,can you share the trace please ?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Your need to confirm your account before you can post a new comment.

· Sign up or log in to comment