Update README.md

README.md

@@ -21,7 +21,7 @@ Rather than relying on static, hardcoded directory trees or predictable regex re
 * **Architecture:** LoRA fine-tune merged into FP16 and quantized to Q8_0 GGUF.
 * **Base Model:** `google/gemma-4-E2B-it`
 * **Target Environment:** Android 14 (API Level 34) shell simulation.
-* **Format:** GGUF (Optimized for edge deployment via `llama.cpp` or similar inference engines).
+* **Format:** LoRA
 
 ### Training Data
 This model was fine-tuned exclusively against the `TitleOS/ADB-CursedHoneycomb` dataset. The dataset consists of 250 curated, synthetic ChatML conversational structures mapping standard, aggressive, and exploratory ADB commands to their corresponding Android 14 outputs generated by Gemini 3.1 Flash-Lite.