better token handling

also fixed windows setup bug requiring to open twice to actually setup venv

HF Login Snippet Kaggle.py

@@ -16,8 +16,10 @@ if os.environ.get('KAGGLE_KERNEL_RUN_TYPE', None) is not None: #check if user in
                    Set your secrets with the secrets add-on on the top of the screen.
              ''')
 if get_token() is not None:
-    #if the token is found then log in:
-    login(get_token())
+    try:
+        login(get_token()) #attempt to login with token found
+    except ValueError:
+        login(input("API token is no longer valid. Enter your new HuggingFace (WRITE) token: ")) #if token is invalid then prompt user to provide new token
 else:
     #if the token is not found then prompt user to provide it:
     login(input("API token not detected. Enter your HuggingFace (WRITE) token: "))

HF Login Snippet.py

@@ -16,13 +16,17 @@ def clear_screen():
 
 #get token
 if get_token() is not None:
-    #if the token is found in either HF_TOKEN or cli login then log in:
-    login(get_token())
     tfound = 'true' #remove if lines 27-34 removed
+    #if the token is found in either HF_TOKEN or cli login then log in:
+    try:
+        login(get_token()) #attempt to login with token found
+    except ValueError:
+        login(input("API token is no longer valid. Enter your new HuggingFace (WRITE) token: ")) #if token is invalid then prompt user to provide new token
+    tfound = 'false' #remove if lines 47-55 removed
 else:
     #if the token is not found then prompt user to provide it:
     login(input("API token not detected. Enter your HuggingFace (WRITE) token: ")) # can remove "(WRITE)" if not required
-    tfound = 'false' #remove if lines 27-34 removed
+    tfound = 'false' #remove if lines 47-55 removed
 
 #if the token is read only then prompt user to provide a write token (Only required if user needs a WRITE token, remove if READ is enough):
 while True:
@@ -30,8 +34,8 @@ while True:
         clear_screen()
         if os.environ.get('HF_TOKEN', None) is not None: #if environ finds HF_TOKEN as write then display following text and exit:
             print(f'''
-          You have the environment variable HF_TOKEN set.
-          You cannot log in.
+                    You have the environment variable HF_TOKEN set.
+                                    You cannot log in.
           Either set the environment variable to a (WRITE) token or remove it.
           ''')
             input("Press enter to continue.")

auto-exl2-upload/INSTRUCTIONS.txt

@@ -23,7 +23,7 @@ Only python 3.8 - 3.12 is known to work. If you have a higher/lower version of p
 
 
 
-First setup your environment by using either windows.bat or linux.sh.
+First setup your environment by using either windows.bat or linux.sh. If you want to upgrade your exllama version, you can run the setup script again.
 
 After setup is complete then you'll have a file called start-quant. Use this to run the quant script.
 
@@ -32,7 +32,7 @@ Make sure to also have a lot of RAM depending on the model. Have noticed gemma t
 
 If you close the terminal or the terminal crashes, check the last BPW it was on and enter the remaining quants you wanted. It should be able to pick up where it left off. Don't type the BPW of completed quants as it will start from the beginning. You may also use ctrl + c to pause at any time during the quant process.
 
-To add more options to the quantization process, you can add them to line 189. All options: https://github.com/turboderp/exllamav2/blob/master/doc/convert.md
+To add more options to the quantization process, you can add them to line 199. All options: https://github.com/turboderp/exllamav2/blob/master/doc/convert.md
 
 Things may break in the future as it downloads the latest version of all the dependencies which may either change names or how they work. If something breaks, please open a discussion at https://huggingface.co/Anthonyg5005/hf-scripts/discussions
 

auto-exl2-upload/auto-exl2-upload.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f382cbbc575ab51aa2881601ff1e0fbaaba349c39cf583154f2cc0121e68b7
-size 8281
+oid sha256:592f8d6daa3245f7d76fd0c73c197580a3c51eb68690541a1c4e7ddedafb8a6b
+size 8402

auto-exl2-upload/exl2-quant.py

@@ -28,6 +28,12 @@ def clear_screen():
     os.system(osclear)
 
 #get token
+if os.environ.get('HF_TOKEN', None) is not None:
+    try:
+        login(get_token())
+    except ValueError:
+        print("You have an invalid token set in your environment variable HF_TOKEN. This will cause issues with this script\nRemove the variable or set it to a valid WRITE token.")
+        sys.exit("Exiting...")
 if os.environ.get('KAGGLE_KERNEL_RUN_TYPE', None) is not None: #check if user in kaggle
     from kaggle_secrets import UserSecretsClient # type: ignore
     from kaggle_web_client import BackendError # type: ignore
@@ -40,9 +46,13 @@ if os.environ.get('KAGGLE_KERNEL_RUN_TYPE', None) is not None: #check if user in
                    Set your secrets with the secrets add-on on the top of the screen.
              ''')
 if get_token() is not None:
-    #if the token is found then log in:
-    login(get_token())
-    tfound = "Where are my doritos?" #doesn't matter what this is, only false is used
+    tfound = 'true'
+    #if the token is found in either HF_TOKEN or cli login then log in:
+    try:
+        login(get_token())
+    except ValueError:
+        login(input("API token is no longer valid. Enter your new HuggingFace (WRITE) token: "))
+    tfound = 'false'
 else:
     #if the token is not found then prompt user to provide it:
     login(input("API token not detected. Enter your HuggingFace (WRITE) token: "))
@@ -54,7 +64,7 @@ while True:
         clear_screen()
         if os.environ.get('HF_TOKEN', None) is not None: #if environ finds HF_TOKEN as read-only then display following text and exit:
             print('''
-                  You have the environment variable HF_TOKEN set.
+            You have the environment variable HF_TOKEN set to a 'READ' token.
                                  You cannot log in.
           Either set the environment variable to a 'WRITE' token or remove it.
                   ''')

auto-exl2-upload/windows-setup.bat

@@ -3,15 +3,17 @@
 setlocal
 
 REM check if "venv" subdirectory exists, if not, create one
+set reinst=n
 if not exist "venv\" (
     python -m venv venv
+    set newvenv=y
 ) else (
     set /p reinst="venv directory already exists. Looking to upgrade/reinstall exllama? (will reinstall python venv) (y/n) "
 )
 if "%reinst%"=="y" (
     rmdir /s /q venv
     python -m venv venv
-) else (
+) else if not "%newvenv%"=="y" (
     exit
 )
 

exl2-multi-quant-local/INSTRUCTIONS.txt

@@ -23,7 +23,7 @@ Only python 3.8 - 3.12 is known to work. If you have a higher/lower version of p
 
 
 
-First setup your environment by using either windows.bat or linux.sh.
+First setup your environment by using either windows.bat or linux.sh. If you want to upgrade your exllama version, you can run the setup script again.
 
 After setup is complete then you'll have a file called start-quant. Use this to run the quant script.
 
@@ -32,7 +32,7 @@ Make sure to also have a lot of RAM depending on the model. Have noticed gemma t
 
 If you close the terminal or the terminal crashes, check the last BPW it was on and enter the remaining quants you wanted. It should be able to pick up where it left off. Don't type the BPW of completed quants as it will start from the beginning. You may also use ctrl + c to pause at any time during the quant process.
 
-To add more options to the quantization process, you can add them to line 140. All options: https://github.com/turboderp/exllamav2/blob/master/doc/convert.md
+To add more options to the quantization process, you can add them to line 145. All options: https://github.com/turboderp/exllamav2/blob/master/doc/convert.md
 
 Things may break in the future as it downloads the latest version of all the dependencies which may either change names or how they work. If something breaks, please open a discussion at https://huggingface.co/Anthonyg5005/hf-scripts/discussions
 

exl2-multi-quant-local/exl2-multi-quant-local.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3217afee2edb741085fad1cab95486ed92617794cff1b306a63edd29869330
-size 7251
+oid sha256:5b939c9a6f47484cf54048980107e8a086f4b6fa4fb1c94f36226d726baff766
+size 7227

exl2-multi-quant-local/exl2-quant.py

@@ -1,6 +1,6 @@
 #usually it's what is on the inside that counts, not this time. This script is a mess, but at least it works.
 #import required modules
-from huggingface_hub import login, get_token, whoami, repo_exists
+from huggingface_hub import login, logout, get_token, whoami, repo_exists
 import os
 import sys
 import subprocess
@@ -29,21 +29,26 @@ def clear_screen():
     os.system(osclear)
 
 #get token
-if os.environ.get('KAGGLE_KERNEL_RUN_TYPE', None) is not None: #check if user in kaggle
-    from kaggle_secrets import UserSecretsClient # type: ignore
-    from kaggle_web_client import BackendError # type: ignore
+if os.environ.get('HF_TOKEN', None) is not None:
     try:
-        login(UserSecretsClient().get_secret("HF_TOKEN")) #login if token secret found
-    except BackendError: 
-        print('''
-            When using Kaggle, make sure to use the secret key HF_TOKEN with a 'WRITE' token.
-                   This will prevent the need to login every time you run the script.
-                   Set your secrets with the secrets add-on on the top of the screen.
-             ''')
+        login(get_token())
+    except ValueError:
+        print("You have an invalid token set in your environment variable HF_TOKEN. This will cause issues with this script\nRemove the variable or set it to a valid token.")
+        sys.exit("Exiting...")
 if get_token() is not None:
-    #if the token is found then log in:
-    login(get_token())
-    tfound = "true" 
+    tfound = 'true'
+    #if the token is found in either HF_TOKEN or cli login then log in:
+    try:
+        login(get_token())
+    except ValueError:
+        try:
+            login(input("API token is no longer valid. Enter your new HuggingFace token (empty to logout): "))
+        except:
+            logout()
+            print("Logging out... (Unable to access private or gated models)")
+            tfound = 'false but logged out'
+            time.sleep(3)
+        tfound = 'false'
 else:
     #if the token is not found then prompt user to provide it:
     tfound = "false"

exl2-multi-quant-local/windows-setup.bat

@@ -3,15 +3,17 @@
 setlocal
 
 REM check if "venv" subdirectory exists, if not, create one
+set reinst=n
 if not exist "venv\" (
     python -m venv venv
+    set newvenv=y
 ) else (
     set /p reinst="venv directory already exists. Looking to upgrade/reinstall exllama? (will reinstall python venv) (y/n) "
 )
 if "%reinst%"=="y" (
     rmdir /s /q venv
     python -m venv venv
-) else (
+) else if not "%newvenv%"=="y" (
     exit
 )