Fix %tokens command crash

[CyanideByte]

Describe the changes you have made:

• Fixed %tokens command where count_tokens fails to find tokenizer because of openai/ in the model name
• If tokenizer for a model isn't found, defaults to gpt-4 tokenizer

Reference any relevant issue (Fixes #000)

• I have performed a self-review of my code:

I have tested the code on the following OS:

• Windows
• MacOS
• Linux

AI Language Model (if applicable)

• GPT4
• GPT3
• Llama 7B
• Llama 13B
• Llama 34B
• Huggingface model (Please specify which one)

[KillianLucas]

Clean fix! Thanks @CyanideByte. Really like that it gives an estimation if it can't find it. Merging.