Category: Tutorial

Categories
Interactive HPC Supercomputing Tutorial

Video Tutorial: LLM Text Classification

The purpose of this webinar is to demonstrate how to perform automated text classification using pre-trained, open-source large language models (LLMs). The efficiency that This webinar demonstrates how to perform automated text classification using pre-trained, open-source large language models (LLMs). The use case is classification of text according to sentiment, but the general workflow is applicable to many other text classification tasks.

In the webinar, it is demonstrated how to:

  • Retrieve text data from online sources
  • Store and prepare the data for analysis
  • Set up an LLM text classifier
  • Perform the text classification
  • Use a web app for human validation of the classification result

Time stamps:

00:00: Introduction and agenda
02:04: Terminology and UCloud workflow outline
08:30: Best practices in web scraping
11:30: Setting up the UCloud workflow
18:30: Scraping and storing the data
27:06: Setting up the the classification pipeline
42:15: Classifying the data and analyzing the results
57:27: Creating a web app for result validation by humans

All scripts used in the webinar can be found here: https://github.com/JHavstein/ucloud-workshop-text-classification-using-LLMs

Sign up for our newsletter and stay updated on future webinars.

Categories
Application Supercomputing Tutorial Webinars & Tutorials - video Workshop

Video Tutorial: Learn to Use CVAT for AI-Assisted Labeling

CVAT, Computer Vision Annotation Tool, is an interactive video and image annotation tool, designed to facilitate the annotation of video and image data and accelerate the creation of high-quality datasets for computer vision tasks. CVAT is available on the UCloud platform, in the Application Store.

The webinar will show how to use CVAT on UCloud to:

Label and annotate data with the help of AI and OpenCV tools, including:

  • Use of cvat-cli
  • Run built-in model for detection and auto-annotation
  • Use of GPUS with built in models for faster annotation
  • Adding custom models (e.g. YOLO)

Efficiently manage large visual datasets with MinIO:

  • Allow CVAT to directly pull images from your UCloud MinIO buckets for annotation and export annotated data back, reducing manual imports/exports and ensuring data availability.

Using UCloud allows users to create fully reproducible and secure workflows that leverage high performance computing resources. Those features are often necessary for large dataset and accurate computer vision tasks.

Target audience: Researchers across all Departments, particularly who require high-precision data labeling, AI interested.

Technical Level: Basic to Intermediate

Sign up for our newsletter and stay updated on future webinars.

Categories
Supercomputing Tutorial UCloud Webinars & Tutorials - video Workshop

Webinar Recording: Getting Started With UCloud

In this video tutorial you will watch a hands-on introduction to UCloud, the national research platform for compute, storage, and applications. The session is designed to help new users get started with UCloud and understand how to use the platform for research, teaching, and project work.

In the recording, we guide you through how to:

  • Log in to UCloud and navigate the dashboard
  • Understand key concepts such as projects, resources, and applications
  • Run your first job and apply for additional compute and storage resources
  • Manage files and collaborate using project workspaces
  • Explore the application catalogue and job submission options
  • Discover new features introduced in UCloud 4.0

This recording is relevant for students, researchers, and new UCloud users across all disciplines.

UCloud is beginner-friendly and does not require any technical background or prior experience with cloud computing.

Timestamps

00:00 – 02:20: Introduction 
What UCloud is, who it’s for, and what the webinar will cover.

02:20 – 03:50: Key terms you need to know
Simple explanations of essential concepts used throughout the platform.

03:50 – 04:30: Support resources and useful links
Where to find help on interactivehpc.dk and additional documentation.

04:30 – 06:10: Login process and UCloud dashboard overview
How to log in and navigate the main dashboard.

06:10 – 08:30: Running your first job
A quick walkthrough of launching an application on UCloud.

08:30 – 14:00: Applying for resources
How to request compute and storage resources for your project.

14:00 – 17:20: File system and Drives
How file storage works and how to manage your data.

17:20 – 18:00: Personal workspace vs project workspace
Key differences and when to use each.

18:00 – 21:30: Managing a UCloud project
Members, settings, allocations, and collaboration.

21:30 – 23:50: Resources page
Public and IP links, SSH keys, and related settings.

23:50 – 25:40: Application catalogue and documentation
How to find apps and access relevant guides.

25:40 – 28:50: Job submission page options
Configuring applications before starting a job.

28:50 – 29:50: Running job view
Monitoring jobs and understanding job status.

29:50 – 32:00: Work folder, output files, and Runs page
Where to find results, logs, and job history.

32:00 – 35:40: What’s new in UCloud 4.0
Command palette, file tree, Syncthing and usage page.

35:40 – 36:08: Conclusion and next steps
Summary and where to find further resources.

Categories
Application Interactive HPC Research Supercomputing Tutorial Workshop

Workshop 26/2: CVAT – AI-Assisted Labeling

Date: February 26, 2026

Time: 13:15 to 14:30 CET

Location: Online via Zoom

CVAT, Computer Vision Annotation Tool, is an interactive video and image annotation tool, designed to facilitate the annotation of video and image data and accelerate the creation of high-quality datasets for computer vision tasks. CVAT is available on the UCloud platform, in the Application Store.

The webinar will show how to use CVAT on UCloud to:

Label and annotate data with the help of AI and OpenCV tools, including:

  • Use of cvat-cli
  • Run built-in model for detection and auto-annotation
  • Use of GPUS with built in models for faster annotation
  • Adding custom models (e.g. YOLO)

Efficiently manage large visual datasets with MinIO:

  • Allow CVAT to directly pull images from your UCloud MinIO buckets for annotation and export annotated data back, reducing manual imports/exports and ensuring data availability.

Using UCloud allows users to create fully reproducible and secure workflows that leverage high performance computing resources. Those features are often necessary for large dataset and accurate computer vision tasks.

Target audience: Researchers across all Departments, particularly who require high-precision data labeling, AI interested.

Technical Level: Basic to Intermediate

Sign up for the CVAT workshop

Categories
Interactive HPC Supercomputing Tutorial Workshop

Workshop 19/2: Text classification using large language models

Date: 19 February 2026
Time: 13:15 – 14:30 (CET)
Location: Online, via Zoom

The purpose of this webinar is to demonstrate how to perform automated text classification using pre-trained, open-source large language models (LLMs). The efficiency that LLMs bring to otherwise laboursome workflows, such as text classification, makes it possible to work with much larger text corpora across all fields of research. The use case will focus on classifying text according to sentiment, but the general workflow is applicable to many other text classification tasks.

In the webinar, we will create a complete workflow which will consist of the following parts:

  1. Retrieving text data from online sources
  2. Storing and preparing the data for analysis
  3. Setting up the LLM text classifier
  4. Performing the text classification
  5. Displaying the results (for validation etc.)

The workflow will be set up on the UCloud platform. Using UCloud allows users to create fully reproducible and secure workflows that leverage high performance computing resources which are often necessary to run LLMs locally.

Sign up for the Text Classification workshop

Categories
Application Interactive HPC Supercomputing Tutorial Webinars & Tutorials - video Workshop

Webinar recording: Learn to record and transcribe securely with the Dictaphone app

In this webinar recording, you will watch a hands-on workshop introducing Dictaphone – a UCloud application that enables researchers to securely record and transcribe interviews directly from their own devices, even when working with sensitive data. 

In the recording, we guide you through how to: 

  • Record interviews and conversations using Dictaphone on your laptop or smartphone 
    Audio is streamed in real time to the secure UCloud backend, ensuring that no data is stored locally on your device – making Dictaphone well suited for handling sensitive data. 
  • Automatically transcribe recordings within the same workflow
    Dictaphone includes built-in transcription functionality, allowing you to convert speech to text quickly and efficiently. 
  • Make the most of Dictaphone, including tips, additional features, and real research use cases. 

This recording is relevant for researchers across all departments as well as students. 

Dictaphone is a beginner-friendly application and does not require any technical background. 

Time stamps 

  • 00:00 – 06:25: Introduction and getting started 
    Requirements, data classifications, and the basic workflow. 
  • 06:25 – 32:15: Live demonstration of Dictaphone 
    How to record and transcribe, and how to navigate the platform before and after recording. 
  • 32:15 – 33:50: Data storage and security 
    How Dictaphone stores data and why it is suitable for sensitive data. 
  • 33:50 – 35:30: Related resources and support 
    Other webinars, related UCloud apps, and contact information. 
  • 35:30 – 43:15: Q&A session 
    Questions from the participants. 
  • 43:15 – 44:22: Wrap-up and next steps 
    Summary and where to find further resources. 

Relevant links 

Categories
Application Tutorial UCloud Workshop

Workshop 19/11: Getting Started with UCloud – Introduction to Features and New Tools

Date: 19 November 2025
Time: 13:00 – 14:30 (CET)
Location: Online, via Zoom

Join us for a hands-on workshop where we guide you through the main features and new tools on UCloud, the national research computing platform that brings together data storage, computation, and collaboration in one place.

In this session, you will learn how to: 

  • Navigate the UCloud interface – understand the menus, and dashboard to access your projects and resources efficiently.
  • Manage files and drives – create and organise project drives, upload and share data, and use the new integrated file editor, terminal and search.
  • Work with projects – set up collaborative projects, manage members and permissions, and monitor resource allocations.
  • Run applications on UCloud – explore the application catalogue, launch and monitor jobs, and use application documentation.
  • Use the latest UCloud features – discover new tools such as the Command Palette for quick actions, integrated Terminal for lightweight file management, real-time job metrics and improved Usage and Allocations pages.

Target audience: Staff, researchers, students, and new UCloud users across all disciplines who want to understand how to get started with UCloud and make the most of its latest features.

Technical Level: Beginner to Intermediate — no prior experience with UCloud required.

Sign up for the Getting Started with UCloud workshop

Categories
Application Supercomputing Tutorial Webinars & Tutorials - video

Webinar Recording: ChatUI and CVAT pipelines

In this video we will guide you through two different AI based workflows, involving ChatUI and CVAT apps.

You will learn how to:

  • Use advanced CVAT features including auto-annotation, algorithmic assistance, management and analytics.
  • Use Chat UI as a flexible interface for hosting of various LLM models, and interact via a chat or API environment.
  • Use ChatUI for semantic search in a knowledge base.
  • Use CVAT as a powerful annotation tool, including image classification, object detection, semantic and instance segmentation, and video / 3D annotations.
Categories
Interactive HPC Teaching Tutorial Webinars & Tutorials - video

Webinar Recording: Transcribing and editing audio transcriptions with Transcriber and Speech Analyzer apps

In this video we will guide you through the complete pipeline of transcribing audio files from speech to text and editing and classifying transcription segments.

In this session, you’ll learn how to:

  • Use Transcriber for transcribing audio/video files. Transcriber is based on Open AI’s Whisper language model. The app can transcribe speech audio to text in various formats and uses the WhisperX package to perform speaker recognition.
  • Navigate the new, simple, drag and drop Transcriber user interface to make it easier for you to use AI to transcribe audio files.
  • Edit and classify the transcriptions with Speech Analyzer. Speech Analyzer is an application built on top of Label Studio, specifically optimized for dialogue analysis. It enables you to label, edit, and annotate transcriptions generated using Transcriber.
  • Perform a comprehensive dialogue analysis on UCloud involving transcribing audio files using Transcriber, followed by transcription analysis with Speech Analyzer.

All workflows will be executed inside a UCloud project environment with access to GPU resources.

Target audience: Researchers across all Departments, particularly Digital Humanities and Social Science, Students, AI interested.

Categories
Interactive HPC Supercomputing Tutorial UCloud Webinars & Tutorials - video Workshop

Webinar recording: Fine-Tuning and Deploying  Large Language Models

In this video we will guide you through the complete pipeline of fine-tuning large language models (LLMs) for specialised tasks such as medical question-answering using NeMo Framework and Triton Inference Server.

  • Prepare and preprocess open-source datasets for fine-tuning.
  • Apply Parameter-Efficient Fine-Tuning (PEFT) using LoRA with NVIDIA NeMo Framework.
  • Deploy optimised LLMs using NVIDIA Triton Inference Server and TensorRT-LLM.
  • Generate a synthetic Q&A dataset using Label Studio connected to a live inference backend.
  • Fine-tune and evaluate your customised LLM for domain-specific applications.

All workflows will be executed inside a UCloud project environment with access to GPU resources.

Target audience: Machine learning practitioners, researchers, and engineers interested in LLM customisation, domain adaptation, or scalable model deployment.

Technical Level: Intermediate to Advanced.

Notebooks: https://github.com/emolinaro/ucloud-workshop-28-05-2025