Hugging Face's logo

ServiceNow-AI
/
Apriel-1.6-15b-Thinker

Image-Text-to-Text
Transformers
Safetensors
llava
image-to-text
conversational
Model card Files
xet
Community
12

vllm bug

#11
by prudant - opened
Discussion
prudant

when tool enable + reasoning the output is corrupt, the thinking tag is not parsed as well
amant555
 ServiceNow-AI org

Hey @prudant can you share a sample of response you are seeing. So we can replicate on our end and fix the issue.

Share the details:

  1. Command used to start the image
  2. The input or a mock input passed
  3. The response you get from the model

Sign up or log in to comment