项目文件夹

文件

T

文件历史

wehub-resource-sync eec33d25b2

Build Wheel / build (3.11) (push) Failing after 1s

详情

Build Wheel / build (3.12) (push) Failing after 0s

详情

pre-commit / pre-commit (push) Failing after 1s

详情

chore: import upstream snapshot with attribution

2026-07-13 12:29:08 +08:00

README.md

chore: import upstream snapshot with attribution

2026-07-13 12:29:08 +08:00

run_mammothmoda2_image_summarize.py

chore: import upstream snapshot with attribution

2026-07-13 12:29:08 +08:00

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