Update README.md

README.md

@@ -1 +1,14 @@
-Llama 30B merged with Chansung's 30B Alpaca Lora. It's working with the newest GPTQ. Quantized using --true-sequential and --act-order optimizations.
+<p><strong>Information</strong></>
+Alpaca 30B 4-bit. It's working with the newest GPTQ. Quantized using --true-sequential and --act-order optimizations.
+
+This was made using Chansung's 30B Alpaca Lora: https://huggingface.co/chansung/alpaca-lora-30b
+
+<p><strong>Benchmarks</strong></p>
+
+Wikitext2: 4.58
+
+Ptb: 7.71
+
+C4: 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