0 Fork 0

Files

T

Yukim1andAdvik 460a5c6b48 [Refactor] Migrate MammothModa2 and OmniVoice to pipeline registry (#4647 )

Signed-off-by: Advik <scince5678@gmail.com>
Signed-off-by: Nightwing-77 <scince5678@gmail.com>
Signed-off-by: zwhzzz0821 <2831474076@qq.com>
Co-authored-by: Advik <scince5678@gmail.com>

2026-07-08 00:44:33 +00:00

README.md

[Refactor] Migrate MammothModa2 and OmniVoice to pipeline registry (#4647 )

2026-07-08 00:44:33 +00:00

run_mammothmoda2_image_summarize.py

[Refactor] Migrate MammothModa2 and OmniVoice to pipeline registry (#4647 )

2026-07-08 00:44:33 +00:00

README.md

MammothModa2-Preview

Text-to-image (T2I) generation has moved to the shared offline image example. See the recipe: recipes/MammothModa2/MammothModa2-Preview.md.

This directory retains the image-understanding (image → text) example below, which is outside the scope of the diffusion model_extras example migration (#4548 / RFC #4539: AR / Omni understanding examples keep dedicated scripts).

Run example (MammothModa2-Preview)

Download model

hf download bytedance-research/MammothModa2-Preview --local-dir ./MammothModa2-Preview

Image Summary

python examples/offline_inference/mammothmodal2_preview/run_mammothmoda2_image_summarize.py \
  --model ./MammothModa2-Preview \
  --deploy-config ./vllm_omni/deploy/mammoth_moda2_ar.yaml \
  --question "Summarize this image." \
  --image ./image.png