Type something to search...
to navigateto selectESC to close

Llama

Building a Multi-Agent Supply Chain Simulation with SmolAgents Library from Hugging Face

Building a Multi-Agent Supply Chain Simulation with SmolAgents Library from Hugging Face

“smolagents — a smol library to build great agents” Supply chain management is a complex domain where multiple entities need to coordi

Read More
Fine-Tuning a Llama-3 LLM and Deploying as a Serverless API on CloudFlare

Fine-Tuning a Llama-3 LLM and Deploying as a Serverless API on CloudFlare

(Or: how I launched my own Llama 3 chatbot at mywebsite.com) 2 years ago, I (like many data scientists) knew absolutely nothing about building websites. I was great at building ML models,

Read More
Building a Multi-agent Internet Research Assistant

Building a Multi-agent Internet Research Assistant

…with OpenAI Swarm & Llama 3.2 (100% local).Let’s build a multi-agent internet research assistant using OpenAI Swarm & Llama 3.2 (100% local): Hands-on tutorial to build a multi-age

Read More
How to Build Your Own OCR Assistant with Streamlit and Llama 3.2-Vision

How to Build Your Own OCR Assistant with Streamlit and Llama 3.2-Vision

Learn with example OCR (Optical Character Recognition) is a tool that helps automate the process of converting images into text. You must have used it in your phone as it is very common no

Read More
How to Fine-Tune Llama-3.2 on your own data: A detailed guide

How to Fine-Tune Llama-3.2 on your own data: A detailed guide

Introduction The release of Llama-3.2 collection from Meta marked an important milestone in the open-s

Read More
Pydantic AI + Web Scraper + Llama 3.3 Python = Powerful AI Research Agent

Pydantic AI + Web Scraper + Llama 3.3 Python = Powerful AI Research Agent

In this video, I have a super quick tutorial showing you how to create a multi-agent chatbot with Pydantic AI, Web Scraper and Llama 3.3 to make a powerful Agent Chatbot for your business or p

Read More
Meta’s Llama 3.3: The Evolution of Open-Source Large Language Models

Meta’s Llama 3.3: The Evolution of Open-Source Large Language Models

Meta’s recent release of Llama 3.3 represents a milestone in the development of large language models (LLMs). It introduces improvements in scale, efficiency, and safety, while remaining open

Read More
Meta Llama3.3 : 70B model alternate for Llama3.1 405B

Meta Llama3.3 : 70B model alternate for Llama3.1 405B

3rd model series in Llama after Llama3.1, Llama3.2 So Meta, in their final release for the year, launched Llama3.3, a 70B GenAI model that has shown some great results and has already b

Read More
How to build an AI-Powered SQL Data Analysis Agent with LangChain and CrewAI

How to build an AI-Powered SQL Data Analysis Agent with LangChain and CrewAI

In today’s data-driven world, automating workflows for data extraction, analysis, and reporting is critical to saving time and improving efficiency. This tutorial walks you through building an AI

Read More
Building a Powerful Local AI Web Search Assistant with Llama 3.2:

Building a Powerful Local AI Web Search Assistant with Llama 3.2:

Combine Large Language Models with Real-Time Web Search for Up-to-Date Answers and Context-Aware Insights 👨🏾‍💻 GitHub ⭐️ | 👔 [LinkedIn](https://www

Read More
Llama 3.2 vs GPT-4 vs OpenAI O1 vs Gemini Ultra vs Claude 3.5: Which AI Model Is Right for You?

Llama 3.2 vs GPT-4 vs OpenAI O1 vs Gemini Ultra vs Claude 3.5: Which AI Model Is Right for You?

Artificial Intelligence has come a long way, and each new model seems to push the boundaries further. Today, I want to share my thoughts on five of the leading AI models out there: Meta’s Llama

Read More
Build Your Talking Voice AI Assistant Locally: Memory-Retaining Chatbot with Streamlit UI…

Build Your Talking Voice AI Assistant Locally: Memory-Retaining Chatbot with Streamlit UI…

Step-by-Step Guide to Developing Your Own Voice AI with Context Memory and Real-Time Chat, Powered by Llama3.1 & Llama3.2 Models The concept of a voice-based personal assistant has gro

Read More
Gemma vs. Llama vs. Mistral: Exploring Smaller AI Models

Gemma vs. Llama vs. Mistral: Exploring Smaller AI Models

A Comparative Study of Small-Scale Language Models: Evaluating Gemma, Llama 3, and Mistral in Reading Comprehension Tasks Introduction Large Language Models (LLMs) have been evolving rapidl

Read More
How NVIDIA Pruned and Distilled Llama 3.1 to Create Minitron 4B and 8B

How NVIDIA Pruned and Distilled Llama 3.1 to Create Minitron 4B and 8B

The new models are using state of the art pruning and distillation techniques.I recently started an AI-focused educational newsletter, that already has over 170,000 subscribers. TheSe

Read More
Llama 3.2: The Next Generation of Lightweight, Instruction-Tuned Language Models: A Hands-On…

Llama 3.2: The Next Generation of Lightweight, Instruction-Tuned Language Models: A Hands-On…

Discover LLaMA 3.2’s Key Innovations in Pruning, Knowledge Distillation, and Multilingual Performance, Plus a Hands-On Tutorial to Run Locally or Through Google Colab 👨🏾‍💻 [GitHub](https://

Read More
Meta’s Llama 4 is Coming Soon Plus: Parallels Brings Apple Intelligence to Windows

Meta’s Llama 4 is Coming Soon Plus: Parallels Brings Apple Intelligence to Windows

Plus: Parallels Brings Apple Intelligence to Windows Welcome to Get The Gist, where every weekday, we share an easy-to-read summary of the latest and greatest developments in AI — ne

Read More
Using Llama 3 for Building AI Agents

Using Llama 3 for Building AI Agents

Comprehensive guide to building AI Agents with Llama 3 function calling capabilities. Introduction Imagine you want to buy something. You visit an e-commerce website and use the sea

Read More
Mistral AI Unveils Ministral 3B and 8B Models Plus: Nvidia Launches AI Model that Outperforms GPT-4

Mistral AI Unveils Ministral 3B and 8B Models Plus: Nvidia Launches AI Model that Outperforms GPT-4

Plus: Nvidia Launches AI Model that Outperforms GPT-4 Welcome to Get The Gist, where every weekday we share an easy-to-read summary of the latest and greatest developments in AI — n

Read More
Fine-tuning LLama 3 with Unsloth

Fine-tuning LLama 3 with Unsloth

In this article I will show you how to fine-tune an LLM (Llama 3 from Meta) using Unsloth. I will also provide a way to use your own custom dataset. **Note

Read More
Llama 3.1 405B — How to Use for Free

Llama 3.1 405B — How to Use for Free

No Local Install Needed Llama 3.1 405B is Meta’s most advanced AI model released in July 2024 — but where can you try it?** LLama 3.1 comes in different versions, including

Read More
Building a Local AI-Powered News Aggregator with Ollama, Swarm, and DuckDuckGo

Building a Local AI-Powered News Aggregator with Ollama, Swarm, and DuckDuckGo

Building a Local AI-Powered News Aggregator with Ollama, Swarm, and DuckDuckGo In today’s fast-paced world, staying up-to-date with the latest news in specific fields can be challenging. What i

Read More
How to Run Nvidia’ llama-3.1-nemotron-70b-instruct Locally

How to Run Nvidia’ llama-3.1-nemotron-70b-instruct Locally

Running large language models (LLMs) locally has become increasingly popular among developers, researchers, and AI enthusiasts. One such model that has gained significant attention is the llama-3.

Read More