Update README.md

README.md

@@ -12,14 +12,34 @@ license: cc-by-4.0
 
 This repo contains GGUF-IQ-Imatrix quantized model files for [Erosumika-7B-v3-0.2](https://huggingface.co/localfultonextractor/Erosumika-7B-v3-0.2).
 
-Quants to be uploaded:
+Quants:
 
          "Q4_K_M", "Q4_K_S", "IQ4_XS", "Q5_K_M", "Q5_K_S",
          "Q6_K", "Q8_0", "IQ3_M", "IQ3_S", "IQ3_XXS"
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/L2l7DXKyLTD6MuL16JPn1.png)
 
-## Model information:
+**What does "Imatrix" mean?**
+
+It stands for **Importance Matrix**, a technique used to improve the quality of quantized models.
+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, especially when the calibration data is diverse.
+[[1]](https://github.com/ggerganov/llama.cpp/discussions/5006) [[2]](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)
+
+For imatrix data generation, kalomaze's `groups_merged.txt` with added roleplay chats was used, you can find it [here](https://huggingface.co/Lewdiculous/Datura_7B-GGUF-Imatrix/blob/main/imatrix-with-rp-format-data.txt). This was just to add a bit more diversity to the data.
+
+**Steps:**
+
+```
+Base⇢ GGUF(F16)⇢ Imatrix-Data(F16)⇢ GGUF(Imatrix-Quants)
+```
+*Using the latest llama.cpp at the time.*
+
+# Submitted model image:
+
+![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/65d4cf2693a0a3744a27536c/KlJMu81ZMKx3JuiPX4n4R.jpeg)
+
+# Original model information:
 
 <h1 style="text-align: center">Erosumika-7B-v3-0.2</h1>
 <h2 style="text-align: center">~Mistral 0.2 Edition~</h1>