Update README.md

README.md

@@ -14,4 +14,6 @@ tags:
 
 Quantized gguf of Tifa-DeepsexV2-7b-NoCot-0325-F16.gguf from https://huggingface.co/ValueFX9507/Tifa-DeepsexV2-7b-MGRPO-GGUF-F16
 
-Quantized with llama.cpp from https://github.com/ggml-org/llama.cpp
+Quantized with llama.cpp from https://github.com/ggml-org/llama.cpp
+
+From my perspective, this version is significantly better than older versions.