Update README.md

README.md

@@ -1,13 +1,14 @@
-</p><strong>Information</strong></p> Alpaca 30B 4-bit. It's working with the newest GPTQ. Quantized using --true-sequential and --act-order 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>--act-order</i> optimizations.</p>
 This was made using Chansung's 30B Alpaca Lora: https://huggingface.co/chansung/alpaca-lora-30b
 
-</p><strong>Benchmarks</strong>
+<p><strong><font size="5">Benchmarks</font></strong></p>
 
-Wikitext2: 4.58
+<strong>Wikitext2</strong>: 4.58
 
-Ptb: 7.71
+<strong>Ptb</strong>: 7.71
 
-C4: 6.32
+<strong>C4</strong>: 6.32
 
-Note: This version does not use grouping, therefore evaluations are minimally higher. However, this version allows fitting the whole model at full context using only 24GB VRAM
+<strong>Note</strong>: This version does not use <i>group size 128</i>, therefore evaluations are minimally higher. As a result, this version allows fitting the whole model at full context using only 24GB VRAM.