Update README.md

README.md

@@ -1,8 +1,13 @@
 <p><strong><font size="5">Information</font></strong></p>
-Alpaca 30B 4-bit working with the newest GPTQ.
+Alpaca 30B 4-bit working with GPTQ versions used in Oobabooga's Text Generation Webui and KoboldAI.
 <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><font size="5">Update 04.06.2023</font></strong></p>
+<p>This is a more recent merge of Chansung's Alpaca Lora which was updated using the clean alpaca dataset as of 04/06/2023 with refined training parameters</p>
+<p><strong>Training Parameters</strong></p>
+<ul><li>num_epochs=10</li><li>cutoff_len=512</li><li>group_by_length</li><li>lora_target_modules='[q_proj,k_proj,v_proj,o_proj]'</li><li>lora_r=16</li><li>micro_batch_size=8</li></ul>
+
 <p><strong><font size="5">Benchmarks</font></strong></p>
 
 <strong>Wikitext2</strong>: 4.58
@@ -11,4 +16,4 @@ This was made using Chansung's 30B Alpaca Lora: https://huggingface.co/chansung/
 
 <strong>C4</strong>: 6.32
 
-<strong>Note</strong>: This version does not use <i>--groupsize 128</i>, therefore evaluations are minimally higher. As a result, this version allows fitting the whole model at full context using only 24GB VRAM.
+<strong>Note</strong>: This version does not use <i>--groupsize 128</i>, therefore evaluations are minimally higher. However, this version allows fitting the whole model at full context using only 24GB VRAM.