Image-Text-to-Text
vllm

Assertion Error for Pixtral-12B-2409

#39
by tigercao2022 - opened

I used the script as shown, and it threw an assertion error. But it is fine using Pixtral-12B-Base-2409

Here is the code I used

from vllm import LLM
from vllm.sampling_params import SamplingParams
model_name = "mistralai/Pixtral-12B-2409"

sampling_params = SamplingParams(max_tokens=8192)

llm = LLM(model=model_name, tokenizer_mode="mistral")

Sign up or log in to comment