Hugging Face's logo

google
/
gemma-4-E2B

Any-to-Any
Transformers
Safetensors
gemma4
image-text-to-text
Model card Files
xet
 Community
10
MaartenGr commited on
Commit
84434eb
·
verified ·
1 Parent(s): 9d53598

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -1
README.md CHANGED
@@ -381,7 +381,10 @@ Compared to Gemma 3, the models use standard `system`, `assistant`, and `user` r
381
 
382
  ### 4. Modality order
383
 
384
- * For optimal performance with multimodal inputs, place image and/or audio content **before** the text in your prompt.
 
 
 
385
 
386
  ### 5. Variable Image Resolution
387
 
 
381
 
382
  ### 4. Modality order
383
 
384
+ For optimal performance with multimodal inputs, place:
385
+
386
+ * Image content **before** the text in your prompt.
387
+ * Audio content **after** the text in your prompt.
388
 
389
  ### 5. Variable Image Resolution
390