Update README.md

README.md

@@ -14,17 +14,27 @@ license: cc-by-nc-4.0
 
 # **GGUF-Imatrix quantizations for [SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE](https://huggingface.co/SanjiWatsuki/Loyal-Toppy-Bruins-Maid-7B-DARE/).**
 
-The new **IQ3_S** quant-option has shown to be better than the old Q3_K_S, so I added that instead of the later. Only supported in `koboldcpp-1.59.1` or higher.
+# What does "Imatrix" mean?
 
-*If you want any specific quantization to be added, feel free to ask.*
+It stands for **Importance Matrix**, a technique used to improve the quality of quantized models.
 
-All credits belong to the [creator](https://huggingface.co/SanjiWatsuki/).
+The **Imatrix** is calculated based on calibration data, and it helps determine the importance of different model activations during the quantization process. The idea is to preserve the most important information during quantization, which can help reduce the loss of model performance.
+
+One of the benefits of using an Imatrix is that it can lead to better model performance, especially when the calibration data is diverse.
+
+For --imatrix data, `imatrix-Loyal-Toppy-Bruins-Maid-7B-DARE-F16.dat` was used.
 
 `Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)`
 
 Using [llama.cpp](https://github.com/ggerganov/llama.cpp/)-[b2280](https://github.com/ggerganov/llama.cpp/releases/tag/b2280).
 
-For --imatrix data, `imatrix-Loyal-Toppy-Bruins-Maid-7B-DARE-F16.dat` was used.
+[[More information in this discussion.]](https://github.com/ggerganov/llama.cpp/discussions/5006)
+
+The new **IQ3_S** quant-option has shown to be better than the old Q3_K_S, so I added that instead of the later. Only supported in `koboldcpp-1.59.1` or higher.
+
+*If you want any specific quantization to be added, feel free to ask.*
+
+All credits belong to the [creator](https://huggingface.co/SanjiWatsuki/).
 
 # Original model information: