Update README.md

README.md

@@ -36,6 +36,7 @@ The quantization method included *32-bit* quantization of the following Layers:
 - down_proj
 - lm_head
 Rest of the remaining layers were quantized to *q3_k_l*
+
 ---
 # Model Description
 | Layer Name                   | Role (Short)                                          | Type           |