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.

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

feat(docs): [SCv2] Automatically create and upload a custom HF model to seldon-models in GCS on every new MLServer version #5103

Merged
merged 2 commits into from
Aug 24, 2023
Merged

feat(docs): [SCv2] Automatically create and upload a custom HF model to seldon-models in GCS on every new MLServer version #5103

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
5d9a0f5
V2D-1257 Create and upload a custom HF model to seldon-models in GCS
vtaskow Aug 23, 2023
c08a1c1
Change GCS location to make it obvious it is a custom hf model
vtaskow Aug 23, 2023
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: 17 additions & 2 deletions samples/scripts/models/Makefile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@ TRITON_VERSION=$(shell grep 'nvidia/tritonserver' ../../../scheduler/Makefile |
TRITON_FOLDER=triton_${TRITON_VERSION}

.PHONY: train-all
train-all: iris moviesentiment income income-xgb income-lgb download-mnist-onnx download-cifar10-tensorflow wine-mlflow mnist-pytorch
train-all: iris text-generation-huggingface moviesentiment income income-xgb income-lgb download-mnist-onnx download-cifar10-tensorflow wine-mlflow mnist-pytorch

.PHONY: upload-all
upload-all: upload-iris upload-moviesentiment upload-income upload-income-xgb upload-income-lgb upload-mnist-onnx upload-cifar10-tensorflow upload-wine-mlflow upload-mnist-pytorch
upload-all: upload-iris upload-text-generation-huggingface upload-moviesentiment upload-income upload-income-xgb upload-income-lgb upload-mnist-onnx upload-cifar10-tensorflow upload-wine-mlflow upload-mnist-pytorch

.PHONY: env
env:
Expand All @@ -20,6 +20,7 @@ env:
mlserver-mlflow==${MLSERVER_VERSION} \
mlserver-lightgbm==${MLSERVER_VERSION} \
mlserver-alibi-explain==${MLSERVER_VERSION} \
mlserver-huggingface==${MLSERVER_VERSION} \
requests
wget https://raw.githubusercontent.com/pytorch/examples/main/mnist/requirements.txt -O mnist-pytorch/requirements.txt
.env/bin/pip install -r mnist-pytorch/requirements.txt
Expand All @@ -36,6 +37,20 @@ iris: env
upload-iris:
gsutil cp iris/model.joblib gs://seldon-models/scv2/samples/${MLSERVER_FOLDER}/iris-sklearn/model.joblib

#
# HuggingFace text-generation model
#

.PHONY: text-generation-huggingface
text-generation-huggingface: env
cd text-generation-huggingface && ../.env/bin/python3 train.py


.PHONY: upload-text-generation-huggingface
upload-text-generation-huggingface:
gsutil cp -r text-generation-huggingface/text-generation-model-artefacts/* gs://seldon-models/scv2/samples/${MLSERVER_FOLDER}/custom-text-generation-huggingface/
gsutil cp text-generation-huggingface/model-settings.json gs://seldon-models/scv2/samples/${MLSERVER_FOLDER}/custom-text-generation-huggingface/

#
# movie sentiment SKLearn model
#
Expand Down
1 change: 1 addition & 0 deletions samples/scripts/models/text-generation-huggingface/.gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
text-generation-model-artefacts/
9 changes: 9 additions & 0 deletions samples/scripts/models/text-generation-huggingface/model-settings.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@
{
"name": "transformer",
"implementation": "mlserver_huggingface.HuggingFaceRuntime",
"parameters": {
"extra": {
"task": "text-generation"
}
}
}
19 changes: 19 additions & 0 deletions samples/scripts/models/text-generation-huggingface/train.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
from transformers import (
GPT2Tokenizer,
TFGPT2LMHeadModel,
pipeline,
)


def main() -> None:
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
model = TFGPT2LMHeadModel.from_pretrained("gpt2")

p = pipeline(task="text-generation", model=model, tokenizer=tokenizer)

p.save_pretrained("text-generation-model-artefacts")


if __name__ == "__main__":
print("Building a custom HuggingFace model...")
main()
Loading