Update README.md

README.md

@@ -26,7 +26,7 @@ The current Metharme-13b has been trained as a LoRA, then merged down to the bas
 
 It has also been quantized down to 4Bit using the GPTQ library available here: https://github.com/0cc4m/GPTQ-for-LLaMa
 ```
-python llama.py .\TehVenom_Metharme-13b-Merged c4 --wbits 4 --true-sequential --groupsize 128 --save_safetensors Metharme-13b-GPTQ-4bit-128g.no-act-order.safetensors
+python llama.py .\TehVenom_Metharme-13b-Merged c4 --wbits 8 --act-order --save_safetensors Metharme-13b-GPTQ-8bit.act-order.safetensors
 ```
 
 ## Prompting
@@ -124,7 +124,7 @@ Current evals out of the Metharme-13b model: <br>
 				<td>7.038073539733887</td>
 			</tr>
             <tr>
-				<td>Metharme 13b - 4bit - [true-sequential & 128g]</td>
+				<td>Metharme 13b - 8bit - [true-sequential & 128g]</td>
 				<td>TBD</td>
 				<td>TBD</td>
 				<td>TBD</td>