Hugging Face's logo

baselabs
/
mammoth-1

Text Classification
Transformers
Safetensors
English
qwen3_5
image-text-to-text
decision-model
classification
calibration
routing
guardrails
vision
multimodal
baseten
Model card Files
xet
 Community
3

Fix Mammoth’s CLI selecting the wrong engine

#3
by sheppo - opened
base: refs/heads/main
←
from: refs/pr/3
Discussion Files changed
+87
-0
sheppo

I noticed qev serve selects the multimodal engine because Mammoth’s config includes vision_config. That engine misses the block-bidirectional attention handling in serve.patch.

This change routes block-bidirectional checkpoints through the patched text engine, matching the model card’s Python example. Explicit --multimodal requests for these checkpoints fail with a clear error.

Checks: patch applies to the pinned runtime; routing regression fails before and passes after. No new GPU inference run.
Fix Mammoth’s CLI selecting the wrong engine3881ab5b
michaelfeil
 baselabs org

@sheppo thanks for your pr. We are reading the mutlimodal_overrides in config.json
Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment