Update README.md

README.md

@@ -51,10 +51,11 @@ Using [llama.cpp quantize cae9fb4](https://github.com/ggerganov/llama.cpp/commit
 
 - Bravo IQ1_S worse than Alpha?
 - [Latent loss](https://huggingface.co/Eviation/flux-imatrix/blob/main/images/latent_loss.png)
-- [Per layer quantization cost](https://huggingface.co/Eviation/flux-imatrix/blob/main/images/latent_loss.png) from [chrisgoringe/casting_cost](https://github.com/chrisgoringe/mixed-gguf-converter/blob/main/costs/casting_cost.yaml)
-
+- [Per layer quantization cost](https://huggingface.co/Eviation/flux-imatrix/blob/main/images/casting_cost.png) from [chrisgoringe/casting_cost](https://github.com/chrisgoringe/mixed-gguf-converter/blob/main/costs/casting_cost.yaml)
 
+### Per weight type quantization loss in increasing order:
 | Weight name |
+| ----------- |
 | double_blocks.%d.txt_attn.proj.weight |
 | double_blocks.%d.txt_mod.lin.weight |
 | time_in.in_layer.weight && time_in.out_layer.weight |