From 24e84440b7f7df7ad2794ce2f4671a5abb6a13af Mon Sep 17 00:00:00 2001 From: Extraltodeus Date: Wed, 15 Jul 2026 23:47:41 +0200 Subject: [PATCH] Correct README content and remove duplication Fix formatting and duplicate text in README. --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 0aa3109..431bc2e 100644 --- a/README.md +++ b/README.md @@ -11,8 +11,8 @@ of any Hugging Face LLM, **and export a usable checkpoint**. You chat with a model while a live **Jacobian lens** shows what each layer is "reading," pin and inspect concepts, then **wash** the -model's identity or behavior with a few token-level rules - turn *"I am a large -language model"* into *"I am a large language fish"* - and **export the result as a +model's identity or behavior with a few token-level rules turn *"I am a large +language model"* into *"I am a large language fish"* and **export the result as a standalone model** (full checkpoint, modified layers, or LoRA): standard safetensors weights that load anywhere `transformers` models do.