We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
Any special reason for it? This is regarding the following code in sft.py "tokenizer.pad_token = "<|fim_pad|>"
The text was updated successfully, but these errors were encountered:
Just to be sure that some code does not accidentally mask tokens that are actually used when it tries to mask all padding tokens
Sorry, something went wrong.
@Muennighoff Can you explain a bit more? Will using an existing pad token cause problems with masking?
i think you should use a token for padding that you dont expect to appear in the regular prompt / completion
sorry but why? what is the reason..??
No branches or pull requests
Any special reason for it? This is regarding the following code in sft.py "tokenizer.pad_token = "<|fim_pad|>"
The text was updated successfully, but these errors were encountered: