-
Notifications
You must be signed in to change notification settings - Fork 1.4k
add multi-modal (vision + language) transformers #2962
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.
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
Conversation
Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
|
/build |
|
/black |
Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
|
/build |
|
/black |
Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
|
/build |
|
/black |
Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
|
/build |
|
/black |
|
Hi @wyli , this PR allows for highly flexible specification of the model for BERT config. Users can simply specify them without any restrictions. It has passed all the tests. Let me know if anything else is needed, otherwise should be good for merging. Thanks |
thanks, it looks good to me. please remove the changes in |
Thanks @wyli. Yes I think there were automatically generated. They maybe triggered to be generated again in future PRs. |
Signed-off-by: ahatamizadeh <ahatamizadeh@nvidia.com>
|
/build |
|
/black |
Just submitted another PR to address this. |
|
I've added some basic docs, still this module needs better paper references and general info. this could be done in some follow-up PRs. |
|
/build |
wyli
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
looks good to me, it requires follow-up documentation/tutorial to show the usages
Fixes #2775
Fixes #2776
Fixes #2777 .
Status
This pull request adds the full pipeline and support for multimodal (vision + language ) transformers. The transformers implementation follow Huggingface repository.
Types of changes
./runtests.sh -f -u --net --coverage../runtests.sh --quick --unittests.make htmlcommand in thedocs/folder.