Custom tokenizer does not work with setup script

[forestoak777]

Setting a custom tokenizer in the llm section of the settings-local.yaml file did not change the value in the privateGPT/settings/settings python script, so the setup script ended up setting the tokenizer name to 'None', and so the setup script crashed. I did a temporary fix by just putting in the literal string right into the private_gpt/settings/settings.py LLMSettings class in the tokenizer field, where None was.

LLM model downloaded!
Downloading tokenizer None

...
(A BUNCH OF PYTHON ERROR STUFF)
...

Repository Not Found for url: https://huggingface.co/None/resolve/main/tokenizer_config.json.
Please make sure you specified the correct `repo_id` and `repo_type`.
If you are trying to access a private or gated repo, make sure you are authenticated.
Invalid username or password.

[forestoak777]

If you are looking for a temporary fix to this, see the last sentence in the issue above.

[ItsCRC]

I added tokenizer: mistralai/Mistral-7B-Instruct-v0.2 in settings.yaml under llm