Generative AI and Open Source Models: Hands-On Practice with Hugging Face Models

Focused View

Harpreet Sahota

1:52:11

0 View

01 - Introduction

01 - Fine-tune your AI Hands-on practice with Hugging Face models.mp4

00:54

02 - 1. Getting Started

01 - How do LLMs generate text.mp4

05:56

02 - Overview of the Hugging Face platform.mp4

03:20

03 - Accessing GPUs.mp4

03:55

03 - 2. Tokenizer

01 - What is tokenization.mp4

04:48

02 - Inspecting a tokenizer.mp4

05:23

03 - Encoding and decoding text.mp4

08:36

04 - Tokenizer chat template.mp4

02:31

04 - 3. Exploring Generation Parameters

01 - First generation with a local model.mp4

11:40

02 - Pipelines.mp4

02:24

03 - Introduction to generation parameters.mp4

05:42

04 - Temperature.mp4

10:07

05 - Top-k.mp4

07:02

06 - Top-p.mp4

06:20

07 - Other generation parameters.mp4

06:21

08 - Hugging Face Inference API.mp4

04:00

05 - 4. Decoding Strategies

01 - Greedy search.mp4

04:00

02 - Multinomial sampling.mp4

02:41

03 - Beam search.mp4

03:32

04 - Beam search with multinomial.mp4

01:23

05 - Contrastive search.mp4

04:57

06 - Conclusion

01 - Interesting technical resources.mp4

02:06

02 - NVIDIA NIM API.mp4

04:33

Description

Large language models (LLMs) are becoming increasingly crucial in various industries. This course with instructor Harpreet Sahota offers a deep dive into the inner workings of text generation using LLMs. Learn about the importance of tokenization, special tokens, and chat templates in text generation. Explore how to manipulate the next selected token and gain a technical and intuitive understanding of generation parameters such as temperature, top-p, top-k, repetition penalty, length penalty, and bad words list. Discover how these parameters can be combined to form powerful decoding strategies, including greedy search, multinomial sampling, beam search, and contrastive search. Gain hands-on experience using the Hugging Face text generation API and get a sneak peek into interacting with the NVIDIA NIM API to explore larger models. By the end of this course, you'll have a solid foundation in controlling text generation with LLMs, enabling you to apply these skills in real-world scenarios.

More details

User Reviews

Rating

average 0

Total votes0

Focused display

Artificial Intelligence

Harpreet Sahota

Instructor's Courses

Linkedin Learning

View courses Linkedin Learning

LinkedIn Learning is an American online learning provider. It provides video courses taught by industry experts in software, creative, and business skills. It is a subsidiary of LinkedIn. All the courses on LinkedIn fall into four categories: Business, Creative, Technology and Certifications. It was founded in 1995 by Lynda Weinman as Lynda.com before being acquired by LinkedIn in 2015. Microsoft acquired LinkedIn in December 2016.