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.

Sign up for GitHub

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

Jump to bottom

Smlo-talk dataset to fine tune pythia - what about tokenizer? #103

Open

fabiomatricardi opened this issue Dec 14, 2024 · 0 comments

fabiomatricardi commented Dec 14, 2024

Hi, due to hardware requirements it may be useful to start with a super-small LLM.
If I want to go for a Pythia base model, how do I have to change the code? certainly pythia does not have a token id for the special tokens in the chatML template.
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant

how it can be done?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment