format quant steps

README.md

@@ -14,7 +14,8 @@ tags:
 Azure_Dusk-v0.2
 
 **Description:** <br>
-"Following up on Crimson_Dawn-v0.2 we have Azure_Dusk-v0.2! Training on Mistral-Nemo-Base-2407 this time I've added significantly more data, as well as trained using RSLoRA as opposed to regular LoRA. Another key change is training on ChatML as opposed to Mistral Formatting." – Author. <br>
+"Following up on Crimson_Dawn-v0.2 we have Azure_Dusk-v0.2! Training on Mistral-Nemo-Base-2407 this time I've added significantly more data, as well as trained using RSLoRA as opposed to regular LoRA. Another key change is training on ChatML as opposed to Mistral Formatting." <br>
+– by Author. <br>
 
 As described, use the ChatML prompt format. <br>
 
@@ -27,7 +28,10 @@ As described, use the ChatML prompt format. <br>
 > Original model page: <br>
 > https://huggingface.co/Epiculous/Azure_Dusk-v0.2
 >
-> Quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp): <br>
-> [b3733](https://github.com/ggerganov/llama.cpp/releases/tag/b3733)
-
+> Quantized using [llama.cpp](https://github.com/ggerganov/llama.cpp)-[b3733](https://github.com/ggerganov/llama.cpp/releases/tag/b3733): <br>
+> ```
+> 1. Base⇢ Convert-GGUF(FP16)⇢ Generate-Imatrix-Data(FP16)
+> 2. Base⇢ Convert-GGUF(BF16)⇢ Use-Imatrix-Data(FP16)⇢ Quantize-GGUF(Imatrix-Quants)
+> ```
+> 
 ![model-image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/n3-g_YTk3FY-DBzxXd28E.png)