Update README.md

README.md

@@ -24,7 +24,7 @@ Expect broken or faulty items for the time being. Use at your own discretion.
   - other: ?
 
 # Caesar
-Combined imatrix multiple images 512x512 and 768x768, 25 and 50 steps [city96/flux1-dev-Q8_0](https://huggingface.co/city96/FLUX.1-dev-gguf/blob/main/flux1-dev-Q8_0.gguf) euler
+Combined imatrix multiple images 512x512 and 768x768, 25, 30 and 50 steps [city96/flux1-dev-Q8_0](https://huggingface.co/city96/FLUX.1-dev-gguf/blob/main/flux1-dev-Q8_0.gguf) euler
 
 data: `load_imatrix: loaded 314 importance matrix entries from imatrix_caesar.dat computed on 475 chunks`
 
@@ -33,8 +33,8 @@ Using [llama.cpp quantize cae9fb4](https://github.com/ggerganov/llama.cpp/commit
 Dynamic quantization:
 - img_in, guidance_in.in_layer, final_layer.linear: f32/bf16/f16
 - guidance_in, final_layer: bf16/f16
-- img_attn.qkv, linear1: some two bits up
-- txt_mod.lin, txt_mlp, txt_attn.proj: some one bit down
+- img_attn.qkv, linear1: some layers two bits up
+- txt_mod.lin, txt_mlp, txt_attn.proj: some layers one bit down
 
 ## Experimental from f16