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

Support text models #932

Open

aliencaocao wants to merge 2 commits into NVIDIA-AI-IOT:master from aliencaocao:patch-1

aliencaocao commented Jun 8, 2024 •

edited

Loading

Because how flattener limits to floats as inputs, it will wrongly remove any int inputs that are common in text models e.g. encoded token ids.

Discovered when trying to convert a text transformer for SigLIP in #931

Closes #931

Tested with SigLIP and results matches closely,


          Support int inputs for text models

addf6fe

aliencaocao mentioned this pull request

Can I convert a siglip only and not a siglip based LLM? dusty-nv/NanoLLM#16

Closed


          Fix utf char

d11692c

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

Labels

None yet