Open-source LLMs: Uncensored & secure AI locally with RAG from Udemy

What's inside

Learning objectives

Why open-source llms? differences, advantages, and disadvantages of open-source and closed-source llms
What are llms like chatgpt, llama, mistral, phi3, qwen2-72b-instruct, grok, gemma, etc.
Which llms are available and what should i use? finding "the best llms"
Requirements for using open-source llms locally
Installation and usage of lm studio, anything llm, ollama, and alternative methods for operating llms
Censored vs. uncensored llms
Finetuning an open-source model with huggingface or google colab
Vision (image recognition) with open-source llms: llama3, llava & phi3 vision
Hardware details: gpu offload, cpu, ram, and vram
All about huggingchat: an interface for using open-source llms
System prompts in prompt engineering + function calling
Prompt engineering basics: semantic association, structured & role prompts
Groq: using open-source llms with a fast lpu chip instead of a gpu
Vector databases, embedding models & retrieval-augmented generation (rag)

Creating a local rag chatbot with anything llm & lm studio
Linking ollama & llama 3, and using function calling with llama 3 & anything llm
Function calling for summarizing data, storing, and creating charts with python
Using other features of anything llm and external apis
Tips for better rag apps with firecrawl for website data, more efficient rag with llamaindex & llamaparse for pdfs and csvs
Definition and available tools for ai agents, installation and usage of flowise locally with node (easier than langchain and langgraph)
Creating an ai agent that generates python code and documentation, and using ai agents with function calling, internet access, and three experts
Hosting and usage: which ai agent should you build and external hosting, text-to-speech (tts) with google colab
Finetuning open-source llms with google colab (alpaca + llama-3 8b, unsloth)
Renting gpus with runpod or massed compute
Security aspects: jailbreaks and security risks from attacks on llms with jailbreaks, prompt injections, and data poisoning
Data privacy and security of your data, as well as policies for commercial use and selling generated content
Show more
Show less

Why open-source llms? differences, advantages, and disadvantages of open-source and closed-source llms
What are llms like chatgpt, llama, mistral, phi3, qwen2-72b-instruct, grok, gemma, etc.
Which llms are available and what should i use? finding "the best llms"
Requirements for using open-source llms locally
Installation and usage of lm studio, anything llm, ollama, and alternative methods for operating llms
Censored vs. uncensored llms
Finetuning an open-source model with huggingface or google colab
Vision (image recognition) with open-source llms: llama3, llava & phi3 vision
Hardware details: gpu offload, cpu, ram, and vram
All about huggingchat: an interface for using open-source llms
System prompts in prompt engineering + function calling
Prompt engineering basics: semantic association, structured & role prompts
Groq: using open-source llms with a fast lpu chip instead of a gpu
Vector databases, embedding models & retrieval-augmented generation (rag)
Creating a local rag chatbot with anything llm & lm studio
Linking ollama & llama 3, and using function calling with llama 3 & anything llm
Function calling for summarizing data, storing, and creating charts with python
Using other features of anything llm and external apis
Tips for better rag apps with firecrawl for website data, more efficient rag with llamaindex & llamaparse for pdfs and csvs
Definition and available tools for ai agents, installation and usage of flowise locally with node (easier than langchain and langgraph)
Creating an ai agent that generates python code and documentation, and using ai agents with function calling, internet access, and three experts
Hosting and usage: which ai agent should you build and external hosting, text-to-speech (tts) with google colab
Finetuning open-source llms with google colab (alpaca + llama-3 8b, unsloth)
Renting gpus with runpod or massed compute
Security aspects: jailbreaks and security risks from attacks on llms with jailbreaks, prompt injections, and data poisoning
Data privacy and security of your data, as well as policies for commercial use and selling generated content
Show more
Show less

Syllabus

Introduction and Overview

Welcome

Course Overview

My Goal and Some Tips

Explanation of the Links

Important Links

Why Open-Source LLMs? Differences, Advantages, and Disadvantages

What is this Section about?

What are LLMs like ChatGPT, Llama, Mistral, etc.

Which LLMs are available and what should I use: Finding "The Best LLMs"

Disadvantages of Closed-Source LLMs like ChatGPT, Gemini, and Claude

Advantages and Disadvantages of Open-Source LLMs like Llama3, Mistral & more

Recap: Don't Forget This!

The Easiest Way to Run Open-Source LLMs Locally & What You Need

Requirements for Using Open-Source LLMs Locally: GPU, CPU & Quantization

Installing LM Studio and Alternative Methods for Running LLMs

Using Open-Source Models in LM Studio: Llama 3, Mistral, Phi-3 & more

4 Censored vs. Uncensored LLMs: Llama3 with Dolphin Finetuning

The Use Cases of classic LLMs like Phi-3 Llama and more

Vision (Image Recognition) with Open-Source LLMs: Llama3, Llava & Phi3 Vision

Some Examples of Image Recognition (Vision)

More Details on Hardware: GPU Offload, CPU, RAM, and VRAM

Summary of What You Learned & an Outlook to Lokal Servers & Prompt Engineering

Prompt Engineering for Open-Source LLMs and Their Use in the Cloud

HuggingChat: An Interface for Using Open-Source LLMs

System Prompts: An Important Part of Prompt Engineering

Why is Prompt Engineering Important? [A example]

Semantic Association: The most Importnant Concept you need to understand

The structured Prompt: Copy my Prompts

Instruction Prompting and some Cool Tricks

Role Prompting for LLMs

Shot Prompting: Zero-Shot, One-Shot & Few-Shot Prompts

Reverse Prompt Engineering and the "OK" Trick

Chain of Thought Prompting: Let`s think Step by Step

Tree of Thoughts (ToT) Prompting in LLMs

The Combination of Prompting Concepts

Creating Your Own Assistants in HuggingChat

Groq: Using Open-Source LLMs with a Fast LPU Chip Instead of a GPU

Recap: What You Should Remember

Function Calling, RAG, and Vector Databases with Open-Source LLMs

What Will Be Covered in This Section?

What is Function Calling in LLMs

Vector Databases, Embedding Models & Retrieval-Augmented Generation (RAG)

Installing Anything LLM and Setting Up a Local Server for a RAG Pipeline

Local RAG Chatbot with Anything LLM & LM Studio

Function Calling with Llama 3 & Anything LLM (Searching the Internet)

Function Calling, Summarizing Data, Storing & Creating Charts with Python

Other Features of Anything LLM: TTS and External APIs

Downloading Ollama & Llama 3, Creating & Linking a Local Server

Recap Don't Forget This!

Optimizing RAG Apps: Tips for Data Preparation

What Will Be Covered in This Section: Better RAG, Data & Chunking

Tips for Better RAG Apps: Firecrawl for Your Data from Websites

More Efficient RAG with LlamaIndex & LlamaParse: Data Preparation for PDFs &more

LlamaIndex Update: LlamaParse made easy!

Chunk Size and Chunk Overlap for a Better RAG Application

Recap: What You Learned in This Section

Local AI Agents with Open-Source LLMs

What Will Be Covered in This Section on AI Agents

AI Agents: Definition & Available Tools for Creating Opensource AI-Agents

We use Langchain with Flowise, Locally with Node.js

Installing Flowise with Node.js (JavaScript Runtime Environment)

The Flowise Interface for AI-Agents and RAG ChatBots

Local RAG Chatbot with Flowise, LLama3 & Ollama: A Local Langchain App

Our First AI Agent: Python Code & Documentation with Superwicer and 2 Worker

AI Agents with Function Calling, Internet and Three Experts for Social Media

Which AI Agent Should You Build & External Hosting with Render

Chatbot with Open-Source Models from Huggingface & Embeddings in HTML (Mixtral)

Insanely fast inference with the Groq API

Recap What You Should Remember

Finetuning, Renting GPUs, Open-Source TTS, Finding the BEST LLM & More Tips

What Is This Section About?

Text-to-Speech (TTS) with Google Colab

Moshi Talk to an Open-Source AI

Finetuning an Open-Source Model with Huggingface or Google Colab

Finetuning Open-Source LLMs with Google Colab, Alpaca + Llama-3 8b from Unsloth

What is the Best Open-Source LLM I Should Use?

Llama 3.1 Infos and What Models should you use

Grok from xAI

Renting a GPU with Runpod or Massed Compute if Your Local PC Isn't Enough

Recap: What You Should Remember!

Data Privacy, Security, and What Comes Next?

THE LAST SECTION: What is This About?

Jailbreaks: Security Risks from Attacks on LLMs with Prompts

Prompt Injections: Security Problem of LLMs

Data Poisoning and Backdoor Attacks

Data Privacy and Security: Is Your Data at Risk?

Commercial Use and Selling of AI-Generated Content

My Thanks and What's Next?

Bonus

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Appropriate for learners who want to expand their knowledge and skills in using open-source LLMs for various applications

Provides practical guidance and hands-on experience in running and utilizing open-source LLMs locally

Covers a wide range of topics, from the basics of open-source LLMs to advanced techniques like prompt engineering and function calling

Suitable for learners with some prior understanding of machine learning or natural language processing

Assumes familiarity with concepts such as GPUs and cloud computing, which may require additional learning for beginners

May require access to specialized hardware or software, such as GPUs or cloud computing services, which may incur additional costs

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Open-source LLMs: Uncensored & secure AI locally with RAG with these activities:

Compile a list of LLM Resources

Show steps

Keep your learning resources organized. Create a curated list of useful LLM-related resources (e.g., tutorials, documentation, articles)

Show steps

Search for LLM-related resources online using search engines, social media, or online forums.
Evaluate the relevance and quality of each resource.
Organize your resources into categories (e.g., tutorials, documentation, articles).
Share your list with others who may find it useful.

Review Basic Python Concepts

Show steps

Strengthen your foundation for working with LLMs by refreshing your knowledge of basic Python concepts.

Browse courses on Python

Show steps

Review Python tutorials and documentation.
Complete practice exercises and coding challenges.
Build a small Python project to apply your refreshed knowledge.

Follow Tutorials on Open-Source LLMs

Show steps

Deepen your understanding of open-source LLMs by following tutorials that provide hands-on experience with their APIs and capabilities.

Browse courses on Open Source LLMs

Show steps

Search for tutorials on open-source LLMs using search engines, online forums, or social media.
Choose a tutorial that aligns with your learning goals and skill level.
Follow the tutorial step-by-step and experiment with the LLM API.
Build a small project or experiment to apply what you learned from the tutorial.

Five other activities

Expand to see all activities and additional details

Show all eight activities

Attend an LLM Workshop

Show steps

Learn from experts and connect with peers at an LLM workshop designed to further your understanding of the field.

Show steps

Research and identify LLM workshops that align with your learning goals.
Register for the workshop and prepare any necessary materials.
Attend the workshop and actively participate in the sessions.
Take notes, ask questions, and engage with the workshop facilitators and other attendees.
Follow up after the workshop by applying what you learned to your own projects and initiatives.

Practice LLM Prompt Engineering

Show steps

Mastering LLMs require fluency in giving useful instructions. Sharpen your abilities by practicing LLM prompt engineering.

Show steps

Identify the type of task you want to complete with the LLM (e.g., question answering, code generation).
Brainstorm a list of potential prompts that could be used to complete the task.
Choose the best prompt from your list and test it out with the LLM.
Evaluate the output of the LLM and make any necessary adjustments to your prompt.
Repeat steps 2-4 until you are satisfied with the output of the LLM.

Develop a Presentation on LLM Applications

Show steps

Expand your understanding of LLM applications by researching, analyzing, and presenting on their potential use cases in various industries and domains.

Show steps

Research and identify different industries and domains where LLMs can be applied.
Analyze the potential benefits and challenges of using LLMs in each industry or domain.
Develop a presentation that clearly communicates your findings.
Deliver your presentation to an audience of peers, instructors, or industry professionals.

Write a Blog Post on LLM Ethics

Show steps

Develop a nuanced understanding of LLM ethics by researching, analyzing, and writing a comprehensive blog post on the topic.

Browse courses on AI Ethics

Show steps

Research different ethical considerations related to the use of LLMs.
Analyze the potential benefits and risks of LLMs in society.
Write a blog post that clearly presents your findings and perspectives on LLM ethics.
Publish your blog post on a relevant platform and share it with others.

Build an LLM-powered Chatbot

Show steps

Solidify your understanding of LLMs by designing, developing, and deploying your very own LLM-powered chatbot.

Show steps

Choose an LLM provider and API.
Design the chatbot's user interface and functionality.
Develop the chatbot's backend code.
Deploy the chatbot and test its functionality.
Monitor the chatbot's performance and make improvements as needed.

Career center

Learners who complete Open-source LLMs: Uncensored & secure AI locally with RAG will develop knowledge and skills that may be useful to these careers:

Reading list

We haven't picked any books for this reading list yet.

Open-source LLMs

Uncensored & secure AI locally with RAG

Here's a deal for you

What's inside

Learning objectives

Syllabus

Good to know

Save this course

Activities

Career center

Featured in The Course Notes

Reading list

Share

Similar courses