Skip to content
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

Add all available ONNX models to ORTConfigManager #351

Open
30 of 57 tasks
chainyo opened this issue Aug 16, 2022 · 2 comments
Open
30 of 57 tasks

Add all available ONNX models to ORTConfigManager #351

chainyo opened this issue Aug 16, 2022 · 2 comments
Labels
good first issue Good for newcomers

Comments

@chainyo
Copy link
Contributor

chainyo commented Aug 16, 2022

This issue is linked to the ONNXConfig for all working group created for implementing an ONNXConfig for all available models. Let's extend our work and try to add all models with a fully functional ONNXConfig implemented to ORTConfigManager.

Adding models to ORTConfigManager will allow 🤗 Optimum users to boost even more their model with ONNX optimization capacity!

Feel free to join us in this adventure! Join the org by clicking here

Here is a non-exhaustive list of models that have one ONNXConfig and could be added to ORTConfigManager:

This includes only models with ONNXConfig implemented, if your target model doesn't have an ONNXConfig, please open an issue/or implement it (even cooler) in the 🤗 Transformers repository. Check this issue to know how to do

  • Albert
  • BART
  • BeiT
  • BERT
  • BigBird
  • BigBirdPegasus
  • Blenderbot
  • BlenderbotSmall
  • BLOOM
  • CamemBERT
  • CLIP
  • CodeGen
  • ConvNext
  • ConvBert
  • Data2VecText
  • Data2VecVision
  • Deberta
  • Deberta-v2
  • DeiT
  • DETR
  • Distilbert
  • ELECTRA
  • Flaubert
  • GptBigCode
  • GPT2
  • GPTJ
  • GPT-NEO
  • GPT-NEOX
  • I-BERT
  • LayoutLM
  • LayoutLMv2
  • LayoutLMv3
  • LeViT
  • Llama
  • LongT5
  • M2M100
  • mBART
  • MT5
  • MarianMT
  • MobileBert
  • MobileViT
  • nystromformer
  • OpenAIGPT-2
  • PLBart
  • Pegasus
  • Perceiver
  • ResNet
  • RoFormer
  • RoBERTa
  • SqueezeBERT
  • T5
  • ViT
  • Whisper
  • XLM
  • XLM-RoBERTa
  • XLM-RoBERTa-XL
  • YOLOS

If you want an example of implementation, I did one for MT5 #341.

You need to check how the attention_heads number and hidden_size arguments are named in the original implementation of your target model in the 🤗 Transformers source code. And then add it to the _conf dictionary. Finally, add your implemented model to tests to make it fully functional.

@mszsorondo
Copy link
Contributor

To update the list of supported models: BlenderBot, BLOOM, GptBigCode, GPT-NEOX, GPTJ, LongT5, Llama, mBART, M2M100, nystromformer, Pegasus,T5 ,ViT ,Whisper
@michaelbenayoun @fxmarty is there still interest in advancing with other models?

@chainyo
Copy link
Contributor Author

chainyo commented Aug 11, 2023

Thanks @mszsorondo I just updated the list based on your comment 🙏 .

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
good first issue Good for newcomers
Projects
None yet
Development

No branches or pull requests

3 participants