Running Qwen2 Vision LLM on Hugging Face ZeroGPU API

Explaining my experience running Sparrow Parse with Qwen2 Vision LLM inference on Hugging Face ZeroGPU instance. 

 

Document AI: How To Convert Colab ML Notebook Into FastAPI App

I explain how I converted Donut ML model fine-tuning code implemented as Colab notebook into API running as FastAPI app. I share several hints how to simplify code refactoring efforts. 

 

Optimizing FastAPI for Concurrent Users when Running Hugging Face ML Models

To serve multiple concurrent users accessing FastAPI endpoint running Hugging Face API, you must start the FastAPI app with several workers. It will ensure current user requests will not be blocked if another request is already running. I show and describe it in this video. 

 

Deploying FastAPI Applications to Hugging Face Spaces

In this video, I demonstrate how to deploy a FastAPI backend API to Hugging Face Spaces using Docker. I cover creating a Dockerfile, setting up secrets for FastAPI, and deploying the application on the platform.

     

Donut ML Model Fine-Tuning with Hugging Face API

I explain how Donut ML model can be fine-tuned on your own dataset by following different approaches. Either with PyTorch Lighting or Hugging Face Trainer API. I explain the pros and cons of both and what works best for me.

 

Hugging Face Dataset for Donut Model Fine-Tuning (Document AI)

Hugging Face Dataset is a very convenient way to store and share data for ML model fine-tuning. In this post, I share my experience creating a dataset for fine-tuning the Donut model. I made a set of scripts to generate the dataset, push it to the Hub and test it locally.

 

How To Fine-tune Donut Model

Donut is an awesome Document AI model to extract data from docs. I share my experiences in fine-tuning the model, with CORD dataset, based on example from Transformers Tutorials.

 

Donut 🍩 - ChatGPT for Document AI

Donut - OCR-free Document Understanding Transformer. This ML model can process documents (images, scans) and return JSON structured info about the content. It works for different use cases: form understanding, visual question answering about the document, document image classification.

 

Best Platform for Python Apps Deployment - Hugging Face Spaces with Docker

I walk through Hugging Face Spaces Docker SDK deployment option. I was using it to deploy our Streamlit/Python app Sparrow. So far very happy with Spaces Docker SDK - simple setup, very stable and good runtime performance, HTTPS out of the box, content compression out of the box too.

 

Document Information Extraction Demo on Hugging Face Spaces

This video shows how fine-tuned LayoutLMv2 document understanding and information extraction model runs on Hugging Face Spaces demo environment. I show how data extraction works for different receipts and why you should not rely on OCR which comes pre-configured together with LayoutLMv2 model.

 

Hugging Face LayoutLMv2 Model True Inference

I explain why OCR quality matters for Hugging Face LayoutLMv2 model performance, related to document data classification. If input from OCR is poor, ML classification inference results will be low quality too. This is why it is important to use high quality OCR system to extract text and coordinates from the document, before applying ML solution.

 

Get Receipt Data with Hugging Face ML Model

This tutorial is about how to use fine-tuned Hugging Face model to extract data from scanned receipt documents. We are executing inference action - passing receipt image, along with words and coordinates to the model. As a result, we get back predictions - class labels assigned to each input. This helps to classify document elements and extract correct data. I share a hint on how to match input words with classified labels. Input words and coordinates are expected to be retrieved from separate OCR.

 

Fine-Tuning with Hugging Face Trainer

In this tutorial, I explain how I was using Hugging Face Trainer with PyTorch to fine-tune LayoutLMv2 model for data extraction from the documents (based on CORD dataset with receipts). The advantage of Hugging Face Trainer - it simplifies model fine-tuning pipeline and you can easily upload the model to Hugging Face model hub.

 

Hugging Face Datasets - Example with Receipts Data

Hugging Face Datasets library provides a useful API to work with data for ML model fine tuning. It allows you to load and process any external datasets with your own Python functions. As a result, you will get a unified data interface and could reuse the same API for fine-tuning various Hugging Face models.

 

How To Evaluate Hugging Face Saved Model

You fine-tuned Hugging Face model on Colab GPU and want to evaluate it locally? I explain how to avoid the mistake with labels mapping array. The same labels mapping you used to fine-tune the model, should be used when evaluating (or doing inference) this model on the local environment (or in another Colab session).

Development Workflow with Hugging Face Transformer Model

This tutorial explains how I do app development with Hugging Face Transformer model. Typically the flow involves model fine-tuning on Colab GPU. Fine-tuned model is downloaded to my local development workstation where I continue development and use the model for inference task. To be able to run complex library dependencies locally, my development environment is setup with a remote Python interpreter through PyCharm and Docker.

 

Hugging Face Gradio App on Docker

This quick tutorial is to explain and show how to run Hugging Face model with Gradio UI on Docker.

 

Running Hugging Face LayoutLM Model with PyCharm and Docker

This tutorial explains how to run Hugging Face LayoutLM model locally with PyCharm remote interpreter. This is cool, because a remote interpreter allows you to run and debug your custom logic, while running Hugging Face model and its dependencies in Docker container. I share Dockerfile, which helps to setup all dependencies. Enjoy!

 

Table Query with Hugging Face ML

Yes, you can do a search through a table data with Hugging Face model called TAPAS. I show how it works with sample CSV and example queries. The app runs on Hugging Face Spaces and you can play and upload your own CSV files for a test. Give it a try, maybe ML can replace SQL?

 

Hugging Face Gradio Python UI and CSV Processing

Explaining how to process CSV file uploaded through Gradio UI in Python. Gradio is part of Hugging Face. You will also learn how to define inputs and outputs for Gradio, to render UI components out of the box. Towards the end of the video, I will share a tip on how to read an error message, if the error happens during app development.