mlboydaisuke commited on
Commit
c3206d8
·
verified ·
1 Parent(s): 64d8f33

docs: announce multimodal sibling repo

Browse files
Files changed (1) hide show
  1. README.md +7 -0
README.md CHANGED
@@ -13,6 +13,13 @@ tags:
13
  pipeline_tag: text-generation
14
  ---
15
 
 
 
 
 
 
 
 
16
  ## Use it from Swift
17
 
18
  <!-- swift-usage-begin -->
 
13
  pipeline_tag: text-generation
14
  ---
15
 
16
+ > **🆕 Multimodal version available** — for text + image + video + audio,
17
+ > use [`mlboydaisuke/gemma-4-E4B-multimodal-coreml`](https://huggingface.co/mlboydaisuke/gemma-4-E4B-multimodal-coreml).
18
+ > Same Gemma 4 E4B decoder + ANE-targeted vision encoder + Conformer
19
+ > audio encoder. Validated 2026-05-03 on iPhone 17 Pro at 15.7 tok/s
20
+ > with all four input modalities working. This text-only repo stays
21
+ > available for users who don't need vision/audio.
22
+
23
  ## Use it from Swift
24
 
25
  <!-- swift-usage-begin -->