Skip to content

rwightman

mammut2-moderntext_ViT-B-32.cc12m-qk-lr2e3-b4096

rwightman/mammut2-moderntext_ViT-B-32.cc12m-qk-lr2e3-b4096

mammut2-moderntext_ViT-B-32.cc12m-qk-lr2e3-b4096 is a zero-shot image classification model from rwightman. Use it for the zero-shot image classification task on the model card, and read the license before you ship it in a product. It is set up for open_clip. The card lists the license as apache-2.0.

MaMMUT2 with a modern text decoder (RoPE, RMSNorm, SwiGLU, gated attention, qk-norm, tiktoken r50k, ctx 128) at batch size 4096 -- matching the batch of the CLIP baselines (though still adamw vs their nadamuon). Best…

Downloads · 30 days

11

15% of all-time downloads

All-time downloads

72

Public

Repo size

1.6 GB

Likes

0

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin804 MB · 50%

At a glance

Task
Zero-Shot Image Classification
Library
open_clip
License
apache-2.0
Access
Public
Created
Aug 19, 2026
Updated
Aug 19, 2026
SHA
3350560b
Task
Zero-Shot Image Classification
Library
open_clip
License
apache-2.0
Created
Aug 19, 2026
Updated
Aug 19, 2026