npatta01/pytorch-serving-workshop
Slides and notebook for the workshop on serving bert models in production
This workshop material helps machine learning engineers or MLOps practitioners deploy trained BERT models for real-time inference. It guides you through preparing e-commerce review data, training a DistilBERT model, optimizing it, and finally packaging and serving the model using TorchServe. The outcome is a production-ready system capable of handling live predictions based on text inputs.
No commits in the last 6 months.
Use this if you are a machine learning engineer or MLOps practitioner looking to understand the practical steps involved in taking a text-based machine learning model from training to production deployment.
Not ideal if you are looking for a general introduction to machine learning model training or if you need to deploy models on a platform other than TorchServe.
Stars
25
Forks
13
Language
Jupyter Notebook
License
—
Category
Last pushed
Nov 12, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/npatta01/pytorch-serving-workshop"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
treeverse/dvc
🦉 Data Versioning and ML Experiments
runpod/runpod-python
🐍 | Python library for RunPod API and serverless worker SDK.
microsoft/vscode-jupyter
VS Code Jupyter extension
4paradigm/OpenMLDB
OpenMLDB is an open-source machine learning database that provides a feature platform computing...
uber/petastorm
Petastorm library enables single machine or distributed training and evaluation of deep learning...