Fix some typo

README.md

@@ -1,13 +1,13 @@
 ---
-license: other
+license: mit
 language: en
 tags:
-  - stable-diffusion
-  - transformer
-  - bnb-4bit
-  - quantization
-  - nf4
-  - fp4
+- stable-diffusion
+- transformer
+- bnb-4bit
+- quantization
+- nf4
+- fp4
 ---
 
 # RediDream NSFW I1 Quantized (bnb-4bit: NF4 & FP4)
@@ -34,7 +34,7 @@ This approach reduces memory usage during quantization to ~40 GB and is **entire
 
 ## Performance
 
-- The quantized models perform **similarly** to the original unquantized version.
+- The quantized models perform **similarly** to the original nf4 quantized version.
 - No formal benchmark or deep evaluation has been conducted.
 
 ## Files
@@ -70,4 +70,4 @@ bnb‑4bit performs similarly to Q4_K, sometimes slightly weaker, but with a sma
 
 ## Disclaimer
 
-This quantized model is intended for research and experimentation. Please verify performance and compatibility before use in production environments.
+This quantized model is intended for research and experimentation. Please verify performance and compatibility before use in production environments.