Large language models for text generation

Course code: MLLLMTG

This course is intended for anyone who is fascinated by the capabilities of large language models and generative artificial intelligence and wants to delve into the subject beyond just the level of the average user. Together we will get to know transformers, the basic building blocks of modern language models, introduce the most famous architectures and show how large language models can be used for various applications. No third-party paid account is required for hands-on exercises. We will be using open source models which, when used correctly, are as good as the biggest commercial models.

210 EUR

254 EUR including VAT

Selection of dates

Do you have a question?

+420 731 175 867 edu@edutrainings.cz

Professional
and certified lecturers

Internationally
recognized certifications

Wide range of technical
and soft skills courses

View soft skills courses

Great customer
service

Making courses
exactly to measure your needs

Course dates
Course structure
Prerequisites

Course dates

Starting date: Upon request

Type: In-person/Virtual

Course duration: 1 day

Language: en/cz

Price without VAT: 210 EUR

	Starting date	Place	Type	Course duration	Language	Price without VAT
	Upon request		In-person/Virtual	1 day	en/cz	210 EUR	Register
G	Guaranteed course

Didn't find a suitable date?

Write to us about listing an alternative tailor-made date.

Contact

Course structure

Generative AI for text and images
The evolution of language modeling
Transformers
Types of transformers for language modeling (encoder, decoder, encoder-decoder)
Reinforcement Learning with Human Feedback (RLHF)
Selected models for transformer-based language modeling (BERT, GPT, LLAMA, T5, BART…)
A practical example of text classification using transformers using the HuggingFace library in the Google Colab environment
Prompt engineering: in-context learning, zero shot, one shot and few shot prompting, the most important configuration parameters of generative processes
A practical example of in-context learning using the HuggingFace library in the Google Colab environment
Fine-tuning of large language models and parameter-efficient fine-tuning (LoRA)
Evaluation of language generative models (ROUGE, BLEU)
A practical example of using parameter-efficient fine-tuning using the HuggingFace library in the Google Colab environment
Retrieval Augmented Generation (RAG)