Remove WD folder when done

and added info to instructions

exl2-windows-local/convert-model-auto.bat

@@ -5,4 +5,5 @@ set /p "bpw=Target BPW: "
 mkdir %model%-exl2-%bpw%bpw
 mkdir %model%-exl2-%bpw%bpw-WD
 copy %model%\config.json %model%-exl2-%bpw%bpw-WD
-venv\scripts\python.exe convert.py -i %model% -o %model%-exl2-%bpw%bpw-WD -cf %model%-exl2-%bpw%bpw -b %bpw%
+venv\scripts\python.exe convert.py -i %model% -o %model%-exl2-%bpw%bpw-WD -cf %model%-exl2-%bpw%bpw -b %bpw%
+rmdir /s /q %model%-exl2-%bpw%-WD

exl2-windows-local/instructions.txt

@@ -10,4 +10,6 @@ Haven't done much testing but Visual Studio with desktop development for C++ mig
 
 make sure you setup the environment by using windows-setup.bat
 after everything is done just download a model using download-model.bat
-to quant, use convert-model-auto.bat. Enter the model's folder name, then the BPW for the model
+to quant, use convert-model-auto.bat. Enter the model's folder name, then the BPW for the model
+
+You can always pause the quantization process by pressing Ctrl + C and typing exit. All progress will be stored in the WD (working directory) folder. You can resume where you left off by running the convert-model-auto.bat script with the same arguments you used before.