LLaMa for Developers

سرفصل های دوره

In this course, learn how to customize open-source AI models with one of the most common open-source models, LLaMa (Large Language Model Meta AI). Instructor Denys Linkov shares a hands-on approach to working with LLaMa, explaining LLaMa architecture, prompting, deploying, and training models. He uses a series of Python notebooks to show you how to adapt LLaMa to your use cases and employ it in an enterprise or startup environment.

01 - Introduction

01 - Developing AI models using LLaMA

02 - 1. Introduction to LLaMA

01 - Using LLaMA online

02 - Running LLaMA in a notebook

03 - Accessing LLaMA in an enterprise environment

03 - 2. LLaMA Architecture

01 - The LLaMA architecture

02 - The LLaMA tokenizer

03 - The LLaMA context window

04 - Differences between LLaMA 1 and 2

04 - 3. Fine-Tuning LLaMA

01 - Fine-tuning LLaMA with a few examples

02 - Fine-tuning LLaMA and freezing layers

03 - Fine-tuning with LLaMA using LoRa

04 - Reinforcement learning with RLHF and DPO

05 - Fine-tuning larger LLaMA models

05 - 4. Serving LLaMA

01 - Resources required to serve LLaMA

02 - Quantizing LLaMA

03 - Using TGI for serving LLaMA

04 - Using VLLM for serving LLaMA

05 - Using DeepSpeed for serving LLaMA

06 - Explaining LoRA and SLoRA

07 - Using a vendor for serving LLaMA

06 - 5. Prompting LLaMA

01 - Difference between LLaMA with commercial LLMs

02 - Few shot learning with LLaMA

03 - Chain of thought with LLaMA

04 - Using schemas with LLaMA

05 - Optimizing LLaMA prompts with DSPy

06 - Challenge Generating product tags

07 - Solution Generating product tags

07 - Conclusion

01 - Continue your LlaMA AI model development journey

139,000 تومان

افزودن به سبد خرید

خرید دانلودی فوری

در این روش نیاز به افزودن محصول به سبد خرید و تکمیل اطلاعات نیست و شما پس از وارد کردن ایمیل خود و طی کردن مراحل پرداخت لینک های دریافت محصولات را در ایمیل خود دریافت خواهید کرد.

تولید کننده: LinkedIn Learning (Lynda)