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

1.1 KiB

Raw Blame History

MammothModa2-Preview

Source https://github.com/vllm-project/vllm-omni/tree/main/examples/offline_inference/mammothmodal2_preview.

Run examples (MammothModa2-Preview)

Download model

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

Text-to-Image (T2I)

Text-to-image now runs through the shared offline image example (examples/offline_inference/text_to_image/text_to_image.py). See the recipe recipes/MammothModa2/MammothModa2-Preview.md for the full command and the extra_body knobs (text_guidance_scale, cfg_range, num_inference_steps).

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

Example materials

??? abstract "run_mammothmoda2_image_summarize.py" py --8<-- "examples/offline_inference/mammothmodal2_preview/run_mammothmoda2_image_summarize.py"

1.1 KiB Raw Blame History