Issue(s) with openGPT-X/Teuken-7B-instruct-research-v0.4

[Sythelux]

Describe the bug

I wanted to try the new OpenGPT Model by the EU:

https://huggingface.co/openGPT-X/Teuken-7B-instruct-research-v0.4

upon loading I first had to activate "trust-remote-code" and it crashed with "can't create directory /home/app" I suppose this is an issue by the author of the LLM, though. I fixed it with manually creating a folder under /home/app and set it to rw for the user for now.

The next problem is, that I get a type error with: TypeError: object of type 'int' has no len() in the shared tokenizer. I provide the full log below.

Is there an existing issue for this?

• I have searched the existing issues

Reproduction

in text-gen ui go to the models tab.
on the download field on the right insert "openGPT-X/Teuken-7B-instruct-research-v0.4" and then press download.
wait for the download to be finished.

I had to set "load in 4-bit" and "trust remote code"

go to the chat tab set to instruct and write something.

the model will crash

Screenshot

Logs

Traceback (most recent call last):
  File "/media/AI/text-generation-webui/installer_files/env/lib/python3.11/site-packages/gradio/queueing.py", line 566, in process_events
    response = await route_utils.call_process_api(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/installer_files/env/lib/python3.11/site-packages/gradio/route_utils.py", line 261, in call_process_api
    output = await app.get_blocks().process_api(
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/installer_files/env/lib/python3.11/site-packages/gradio/blocks.py", line 1786, in process_api
    result = await self.call_function(
             ^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/installer_files/env/lib/python3.11/site-packages/gradio/blocks.py", line 1350, in call_function
    prediction = await utils.async_iteration(iterator)
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/installer_files/env/lib/python3.11/site-packages/gradio/utils.py", line 583, in async_iteration
    return await iterator.__anext__()
           ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/installer_files/env/lib/python3.11/site-packages/gradio/utils.py", line 576, in __anext__
    return await anyio.to_thread.run_sync(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/installer_files/env/lib/python3.11/site-packages/anyio/to_thread.py", line 56, in run_sync
    return await get_async_backend().run_sync_in_worker_thread(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/installer_files/env/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 2441, in run_sync_in_worker_thread
    return await future
           ^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/installer_files/env/lib/python3.11/site-packages/anyio/_backends/_asyncio.py", line 943, in run
    result = context.run(func, *args)
             ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/installer_files/env/lib/python3.11/site-packages/gradio/utils.py", line 559, in run_sync_iterator_async
    return next(iterator)
           ^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/installer_files/env/lib/python3.11/site-packages/gradio/utils.py", line 742, in gen_wrapper
    response = next(iterator)
               ^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/modules/chat.py", line 436, in generate_chat_reply_wrapper
    for i, history in enumerate(generate_chat_reply(text, state, regenerate, _continue, loading_message=True, for_ui=True)):
  File "/media/AI/text-generation-webui/modules/chat.py", line 403, in generate_chat_reply
    for history in chatbot_wrapper(text, state, regenerate=regenerate, _continue=_continue, loading_message=loading_message, for_ui=for_ui):
  File "/media/AI/text-generation-webui/modules/chat.py", line 348, in chatbot_wrapper
    prompt = generate_chat_prompt(text, state, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/modules/chat.py", line 200, in generate_chat_prompt
    encoded_length = get_encoded_length(prompt)
                     ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/modules/text_generation.py", line 189, in get_encoded_length
    return len(encode(prompt)[0])
               ^^^^^^^^^^^^^^
  File "/media/AI/text-generation-webui/modules/text_generation.py", line 144, in encode
    if (len(input_ids[0]) > 0 and input_ids[0][0] != shared.tokenizer.bos_token_id) or len(input_ids[0]) == 0:
        ^^^^^^^^^^^^^^^^^
TypeError: object of type 'int' has no len()

System Info

Pop!_OS 24 (Linux, Debian based)
NVIDIA RTX3060