Course Code: ftosllms
Duration: 14 hours
Prerequisites:
  • An understanding of large language models (LLMs) and their architecture
  • Experience with Python and PyTorch
  • Basic familiarity with the Hugging Face ecosystem

Audience

  • ML practitioners
  • AI developers
Overview:

Fine-tuning open-source LLMs is an emerging best practice for organizations that seek to customize AI capabilities in secure, cost-efficient, and private environments.

This instructor-led, live training (online or onsite) is aimed at intermediate-level ML practitioners and AI developers who wish to fine-tune and deploy open-weight models like LLaMA, Mistral, and Qwen for specific business or internal applications.

By the end of this training, participants will be able to:

  • Understand the ecosystem and differences between open-source LLMs.
  • Prepare datasets and fine-tuning configurations for models like LLaMA, Mistral, and Qwen.
  • Execute fine-tuning pipelines using Hugging Face Transformers and PEFT.
  • Evaluate, save, and deploy fine-tuned models in secure environments.

Format of the Course

  • Interactive lecture and discussion.
  • Lots of exercises and practice.
  • Hands-on implementation in a live-lab environment.

Course Customization Options

  • To request a customized training for this course, please contact us to arrange.
Course Outline:

Introduction to Open-Source LLMs

  • What are open-weight models and why they're important
  • Overview of LLaMA, Mistral, Qwen, and other community models
  • Use cases for private, on-premise, or secure deployments

Environment Setup and Tools

  • Installing and configuring Transformers, Datasets, and PEFT libraries
  • Choosing appropriate hardware for fine-tuning
  • Loading pre-trained models from Hugging Face or other repositories

Data Preparation and Preprocessing

  • Dataset formats (instruction tuning, chat data, text-only)
  • Tokenization and sequence management
  • Creating custom datasets and data loaders

Fine-Tuning Techniques

  • Standard full fine-tuning vs. parameter-efficient methods
  • Applying LoRA and QLoRA for efficient fine-tuning
  • Using Trainer API for quick experimentation

Model Evaluation and Optimization

  • Assessing fine-tuned models with generation and accuracy metrics
  • Managing overfitting, generalization, and validation sets
  • Performance tuning tips and logging

Deployment and Private Use

  • Saving and loading models for inference
  • Deploying fine-tuned models in secure enterprise environments
  • On-premise vs. cloud deployment strategies

Case Studies and Use Cases

  • Examples of enterprise use of LLaMA, Mistral, and Qwen
  • Handling multilingual and domain-specific fine-tuning
  • Discussion: Trade-offs between open and closed models

Summary and Next Steps

Sites Published:

United Arab Emirates - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Qatar - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Egypt - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Saudi Arabia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

South Africa - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Brasil - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Canada - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

中国 - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

香港 - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

澳門 - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

台灣 - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

USA - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Österreich - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Schweiz - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Deutschland - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Czech Republic - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Denmark - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Estonia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Finland - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Greece - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Magyarország - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Ireland - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Luxembourg - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Latvia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

España - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Italia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Lithuania - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Nederland - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Norway - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Portugal - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

România - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Sverige - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Türkiye - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Malta - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Belgique - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

France - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

日本 - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Australia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Malaysia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

New Zealand - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Philippines - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Singapore - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Thailand - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Vietnam - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

India - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Argentina - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Chile - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Costa Rica - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Ecuador - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Guatemala - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Colombia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

México - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Panama - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Peru - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Uruguay - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Venezuela - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Polska - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

United Kingdom - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

South Korea - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Pakistan - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Sri Lanka - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Bulgaria - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Bolivia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Indonesia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Kazakhstan - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Moldova - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Morocco - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Tunisia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Kuwait - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Oman - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Slovakia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Kenya - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Nigeria - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Botswana - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Slovenia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Croatia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Serbia - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Bhutan - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Nepal - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)

Uzbekistan - Fine-Tuning Open-Source LLMs (LLaMA, Mistral, Qwen, etc.)