Merge pull request #6 from jllllll/oobabooga-windows

Attempt to Improve Reliability

INSTRUCTIONS.txt

@@ -2,7 +2,7 @@ Thank you for downloading oobabooga/text-generation-webui.
 Here is how to get it up and running:
 
 1. Run the "install" script to install the web UI and its requirements in this folder.
-2. Run the "download" script to download a model of your choice. Change TextOnly variable at top of script to download only config files.
+2. Run the "download-model" script to download a model of your choice. Change TextOnly variable at top of script to download only config files.
 3. Run the "start-webui" script to launch the web UI.
 
 To add flags like --chat, --notebook, --extensions, etc, edit the
@@ -11,3 +11,9 @@ to the line that says "python server.py...".
 
 To get the latest updates in the future, just re-run the "install" script.
 This will only install the updates, so it should be much faster.
+May need to delete '\text-generation-webui\repositories\GPTQ-for-LLaMa' folder if GPTQ-for-LLaMa needs to be updated.
+
+You can open a command-line attached to the virtual environment by running the "micromamba-cmd" script.
+
+This installer uses a custom-built Windows-compatible version of bitsandbytes. Source: https://github.com/acpopescu/bitsandbytes/tree/cmake_windows
+When starting the webui, you may encounter an error referencing cuda 116. Starting the webui again should allow bitsandbytes to detect the correct version.

install.bat

@@ -5,6 +5,9 @@
 @rem using micromamba (an 8mb static-linked single-file binary, conda replacement).
 @rem This enables a user to install this project without manually installing conda and git.
 
+echo WARNING: This script relies on Micromamba which may have issues on some systems when installed under a path with spaces.
+echo          May also have issues with long paths.&& echo.
+
 echo What is your GPU?
 echo.
 echo A) NVIDIA
@@ -26,7 +29,7 @@ if /I "%gpuchoice%" == "A" (
 
 cd /D "%~dp0"
 
-set PATH=%SystemRoot%\system32;%PATH%
+set PATH=%PATH%;%SystemRoot%\system32
 
 set MAMBA_ROOT_PREFIX=%cd%\installer_files\mamba
 set INSTALL_ENV_DIR=%cd%\installer_files\env
@@ -45,7 +48,7 @@ if "%PACKAGES_TO_INSTALL%" NEQ "" (
         echo "Downloading Micromamba from %MICROMAMBA_DOWNLOAD_URL% to %MAMBA_ROOT_PREFIX%\micromamba.exe"
 
         mkdir "%MAMBA_ROOT_PREFIX%"
-        call curl -L "%MICROMAMBA_DOWNLOAD_URL%" > "%MAMBA_ROOT_PREFIX%\micromamba.exe"
+        call curl -L "%MICROMAMBA_DOWNLOAD_URL%" > "%MAMBA_ROOT_PREFIX%\micromamba.exe" || ( echo Micromamba failed to download. && goto end )
 
         @rem test the mamba binary
         echo Micromamba version:
@@ -73,6 +76,7 @@ if exist text-generation-webui\ (
   git pull
 ) else (
   git clone https://github.com/oobabooga/text-generation-webui.git
+  call python -m pip install https://github.com/jllllll/bitsandbytes-windows-webui/raw/main/bitsandbytes-0.37.2-py3-none-any.whl
   cd text-generation-webui || goto end
 )
 call python -m pip install -r requirements.txt --upgrade
@@ -97,20 +101,9 @@ if not exist GPTQ-for-LLaMa\ (
   call python setup_cuda.py install
   if not exist "%INSTALL_ENV_DIR%\lib\site-packages\quant_cuda-0.0.0-py3.10-win-amd64.egg" (
     echo CUDA kernal compilation failed. Will try to install from wheel.
-    curl -LO https://github.com/jllllll/GPTQ-for-LLaMa-Wheels/raw/main/quant_cuda-0.0.0-cp310-cp310-win_amd64.whl
+    call python -m pip install https://github.com/jllllll/GPTQ-for-LLaMa-Wheels/raw/main/quant_cuda-0.0.0-cp310-cp310-win_amd64.whl || ( echo Wheel installation failed. && goto end )
-    call python -m pip install quant_cuda-0.0.0-cp310-cp310-win_amd64.whl || ( echo Wheel installation failed. && goto end )
   )
-  cd ..
 )
-cd ..\..
-
-:bandaid
-curl -LO https://github.com/DeXtmL/bitsandbytes-win-prebuilt/raw/main/libbitsandbytes_cpu.dll
-curl -LO https://github.com/james-things/bitsandbytes-prebuilt-all_arch/raw/main/0.37.0/libbitsandbytes_cudaall.dll
-mv libbitsandbytes_cpu.dll "%INSTALL_ENV_DIR%\lib\site-packages\bitsandbytes"
-mv libbitsandbytes_cudaall.dll "%INSTALL_ENV_DIR%\lib\site-packages\bitsandbytes"
-sed -i "s/if not torch.cuda.is_available(): return 'libsbitsandbytes_cpu.so', None, None, None, None/if torch.cuda.is_available(): return 'libbitsandbytes_cudaall.dll', None, None, None, None\n    else: return 'libbitsandbytes_cpu.dll', None, None, None, None/g" "%INSTALL_ENV_DIR%\lib\site-packages\bitsandbytes\cuda_setup\main.py"
-sed -i "s/ct.cdll.LoadLibrary(binary_path)/ct.cdll.LoadLibrary(str(binary_path))/g" "%INSTALL_ENV_DIR%\lib\site-packages\bitsandbytes\cuda_setup\main.py"
 
 :end
 pause