-
Notifications
You must be signed in to change notification settings - Fork 24
Add goglebert base cased #65
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
base: main
Are you sure you want to change the base?
Add goglebert base cased #65
Conversation
|
@urnotdfs please read the following Contributor License Agreement(CLA). If you agree with the CLA, please reply with the following information.
Contributor License AgreementContribution License AgreementThis Contribution License Agreement (“Agreement”) is agreed to by the party signing below (“You”),
|
This pull request adds support for the
google-bert/bert-base-casedmodel, including configuration and documentation for optimization workflows targeting multiple hardware accelerators. It introduces the model to the registry, provides licensing, and includes example configuration files for OpenVINO optimization and quantization. Additionally, it updates global configuration counters and improves.gitignorehandling for the new model directory.Model Addition and Registry Updates:
google-bert/bert-base-casedto the model registry in.aitk/configs/model_list.json, specifying supported runtimes (QNN, AMDNPU, NvidiaTRTRTX, DML, IntelCPU, IntelGPU, IntelNPU), architecture, status, and relative path..aitk/configs/checks.jsonto reflect the addition of the new model and associated configuration files.Model Directory and Documentation:
google-bert-bert-base-cased/aitkdirectory with aREADME.mddescribing optimization workflows for Qualcomm NPU, AMD NPU, Intel NPU, and NVIDIA/DML GPUs, including a latency/throughput benchmark table.google-bert-bert-base-cased/LICENSE..gitignoreto the model directory to exclude cache and history files except for essential configuration files.Optimization and Quantization Configurations:
bert-base-cased_context_ov_static.json, supporting conversion, quantization, evaluation, and encapsulation for Intel NPU..configfile (bert-base-cased_context_ov_static.json.config) with UI parameters for runtime selection, quantization dataset options, and evaluation toggling.