Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

New install of WSL error with missing Tokeniser #396

Closed
1 task done
manassm opened this issue Mar 18, 2023 · 5 comments
Closed
1 task done

New install of WSL error with missing Tokeniser #396

manassm opened this issue Mar 18, 2023 · 5 comments
Labels
bug Something isn't working

Comments

@manassm
Copy link

manassm commented Mar 18, 2023

Describe the bug

I was using the previous version of the webui with one-click install method until I updated it and it stopped working.
Hence, I tried the new WSL method to install it on my windows system.
But when I thought everything was complete and I tried to run it, it says that some Tokenisers are missing, I guess.
(I don't have CS background so I don't really know the details of what I am talking about.)
Please help to resolve this issue.

Is there an existing issue for this?

  • I have searched the existing issues

Reproduction

(base) ssm05111@username:$ conda activate textgen
(textgen) ssm05111@username:
$ cd text-generation-webui/
(textgen) ssm05111@username:~/text-generation-webui$ python server.py

Screenshot

화면 캡처 2023-03-17 203030

Logs

Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
================================================================================
/home/ssm05111/miniconda3/envs/textgen/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: /home/ssm05111/miniconda3/envs/textgen did not contain libcudart.so as expected! Searching further paths...
  warn(msg)
/home/ssm05111/miniconda3/envs/textgen/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('unix')}
  warn(msg)
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching /usr/local/cuda/lib64...
/home/ssm05111/miniconda3/envs/textgen/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/usr/local/cuda/lib64')}
  warn(msg)
CUDA SETUP: WARNING! libcuda.so not found! Do you have a CUDA driver installed? If you are on a cluster, make sure you are on a CUDA machine!
/home/ssm05111/miniconda3/envs/textgen/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: WARNING: No libcudart.so found! Install CUDA or the cudatoolkit package (anaconda)!
  warn(msg)
/home/ssm05111/miniconda3/envs/textgen/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:136: UserWarning: WARNING: No GPU detected! Check your CUDA paths. Proceeding to load CPU-only library...
  warn(msg)
CUDA SETUP: Loading binary /home/ssm05111/miniconda3/envs/textgen/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cpu.so...
/home/ssm05111/miniconda3/envs/textgen/lib/python3.10/site-packages/bitsandbytes/cextension.py:31: UserWarning: The installed version of bitsandbytes was compiled without GPU support. 8-bit optimizers and GPU quantization are unavailable.
  warn("The installed version of bitsandbytes was compiled without GPU support. "
Loading llama-7b-hf...
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████| 33/33 [00:08<00:00,  3.96it/s]
Traceback (most recent call last):
  File "/home/ssm05111/text-generation-webui/server.py", line 236, in <module>
    shared.model, shared.tokenizer = load_model(shared.model_name)
  File "/home/ssm05111/text-generation-webui/modules/models.py", line 163, in load_model
    tokenizer = AutoTokenizer.from_pretrained(Path(f"models/{shared.model_name}/"))
  File "/home/ssm05111/miniconda3/envs/textgen/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 677, in from_pretrained
    raise ValueError(
ValueError: Tokenizer class LLaMATokenizer does not exist or is not currently imported.

System Info

NVidia 4080
Windows 11
@manassm manassm added the bug Something isn't working label Mar 18, 2023
@CrazyKrow
Copy link

CrazyKrow commented Mar 18, 2023

I had the same problem, you have to rename "LLaMATokenizer" to "LlamaTokenizer" on the tokenizer_config.json from your model. And if you still have CUDA problems try conda install cudatoolkit

@CrazyKrow
Copy link

just type explorer.exe on the wsl terminal and then you should be able to view the files inside the file explorer window. Then you can edit the tokenizer_config.json with notepad.
https://www.fourco.nl/blogs/access-to-wsl-filesystem-in-explorer/

@manassm
Copy link
Author

manassm commented Mar 18, 2023

Thanks for the help. I edited the json file and installed cudatoolkit. It seems like it is kinda working, but I still get these warning signs that I'm not sure if I need to worry about or not.
화면 캡처 2023-03-17 221112

@cpwilson1989
Copy link

Not sure if you've seen this already, but this helped me with that error:
156#issuecomment-1462329713

@manassm
Copy link
Author

manassm commented Mar 18, 2023

@cpwilson1989 I did see that, thanks for the notice though.
I looked for file named libbitsandbytes_cpu.so located in linux machine \wsl.localhost\Ubuntu\home\username\miniconda3\envs\textgen\lib\python3.10\site-packages\bitsandbytes, deleted it, and changed the file name of libbitsandbytes_cuda117.so into libbitsandbytes_cpu.so. It now seems to work (there is still few lines of error but the UI seems to work). Thank you.

@manassm manassm closed this as completed Mar 18, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

3 participants