Update README.md

README.md

@@ -1,12 +1,13 @@
-<p><strong>Information</strong></p>
-Alpaca 30B 4-bit. It's working with the newest GPTQ. Quantized using --true-sequential and --groupsize 128 optimizations.
+<p><strong><font size="5">Information</font></strong></p>
+Alpaca 30B 4-bit working with the newest GPTQ.
+<p>Quantized using <i>--true-sequential</i> and <i>--groupsize 128</i> optimizations.</p>
 This was made using Chansung's 30B Alpaca Lora: https://huggingface.co/chansung/alpaca-lora-30b
 
-<p><strong>Benchmarks</strong></p>
-Wikitext2: 4.37
+<p><strong><font size="5">Benchmarks</font></strong></p>
+<strong>Wikitext2</strong>: 4.37
 
-Ptb: 7.58
+<strong>Ptb</strong>: 7.58
 
-C4: 6.19
+<strong>C4</strong>: 6.19
 
-Note: This version uses grouping, therefore evaluations are better. However, this version takes up more VRAM.
+<strong>Note</strong>: This version uses <i>group size 128</i>, therefore evaluations are better. As a result, this version consumes more VRAM.