Skip to content

Add DeBERTa training and ONNX export pipeline for required phrases extraction #5222

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

Open
Kaushik-Kumar-CEG wants to merge 2 commits into
base: develop
Choose a base branch
from
+5,133 −0
Open

Add DeBERTa training and ONNX export pipeline for required phrases extraction #5222

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4ccfe39
Add required phrase model training and export
Kaushik-Kumar-CEG Aug 31, 2026
676b47f
Harden required phrase model training
Kaushik-Kumar-CEG Sep 7, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 19 additions & 0 deletions etc/requirements-ml.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
# Dependencies for training and exporting the required phrase model.
# Install with: pip install -r etc/requirements-ml.txt

torch>=2.0
transformers==4.57.3
huggingface-hub==0.36.2
sentencepiece>=0.2
protobuf>=3.20
accelerate>=0.33
pytorch-crf==0.7.2
safetensors>=0.4

# Used explicitly for DeBERTa-large training on a 16 GB GPU.
bitsandbytes>=0.43

# ONNX export and CPU verification.
numpy>=1.24
onnx>=1.16
onnxruntime>=1.18
Loading