From 2785df4d08e1e02a992583ee21ad7a96a05bc663 Mon Sep 17 00:00:00 2001
From: Extraltodeus <extraltodeus@gmail.com>
Date: Wed, 15 Jul 2026 18:27:08 +0200
Subject: [PATCH] Update README.md

---
 README.md | 1 +
 1 file changed, 1 insertion(+)

diff --git a/README.md b/README.md
index c5a70dc..0150a35 100644
--- a/README.md
+++ b/README.md
@@ -276,6 +276,7 @@ hf_cache/ only if you run with --hf-cache ./hf_cache (git-ignored)
 - Loading `.gguf` files directly as models is **not** supported — J-Wash loads
   transformers/safetensors models only.
 - Interventions and lens readouts are unavailable on quantized (int8/nf4) weights.
+- Gemma models having a slightly different attention are not as easy to modify.
 
 ## Credits