3 ways to run Llama-3 locally (100% free and without internet):

Meta's new AI—Llama3—beats an old version of GPT-4, Claude 2.1, and GPT-3.5!

You can run it:
- 100% free
- with 100% privacy (no data leaves your machine)

See the comments for an easy way to install 👇

Next level: QLoRA fine-tuning 4-bit Llama 3 8B on iPhone 15 pro.

Incoming (Q)LoRA MLX Swift example by David Koski: github.com/ml-explore/mlx… works with lot's of models (Mistral, Gemma, Phi-2, etc)

Building a ColBERT-powered Retrieval Agent with Memory 🧠🤖

Storing “state” in a RAG pipeline is a key step towards moving beyond single-shot QA into a personalized, conversational assistant. But this leads to challenges - how do you pass conversation history into retrieval and

Fine-tuning Embedding Models for RAG with LoRA 💡

This is a great tutorial (by Mariboo) showcasing how to cleverly subclass LlamaIndex 🦙 finetuning abstractions to finetune any Hugging Face embedding model with LoRA weights, which you can then plug in as a crucial step of any

This project is sick 👇 - learn how to stream a knowledge graph step-by-step by hooking into LLM streaming, partial JSON parsing in LlamaIndex 🦙, and rendering with the Vercel AI SDK 🔥

Streaming text in the UI is standard for any chatbot experience, but streaming visual

An Intro to Building Knowledge Graphs

buff.ly/3UbOZg6 Open Data Science
#AI #MachineLearning #DataScience
Cc AI Tamara McCleary Terence Mills Jean-Baptiste Lefevre Yann Marchand Nicolas Babin

How #AI is shaking up how #sports like rugby, soccer and cricket are played

and could mint big money for sports clubs

fortune.com/europe/2024/04… #fintech #ArtificialIntelligence #MachineLearning #DeepLearning #BigData FORTUNE

AI Brian Ahier Harold Sinnott 📲

#MachineLearning Patterns and Anti-Patterns

buff.ly/3RM5wpI v/ DZone
#AI
Cc Jean-Baptiste Lefevre Kirk Borne AI Dinis Guarda Franco Ronconi 🇮🇹 Digital News Stream

The more I use Llama 3 the more I think that Zuck may have just killed OpenAI and all other large proprietary AI vendors. The gap between latest GPT4 and Llama 70b is virtually non existent. Even if OpenAI releases GPT5 now, 400b Llama 3 is still training and will most likely be

Being able to interpret an #ML model’s hidden representations is key to understanding its behavior. Today we introduce Patchscopes, an approach that trains #LLMs to provide natural language explanations of their own hidden representations. Learn more → goo.gle/4aS5epd

DREAM - a Distributed RAG Experimentation Framework 🧑‍🔬

Building RAG comes with a lot of knobs that you need to tune, and it’s important that you setup the right experimentation infrastructure to build production RAG.

This project by Aishwarya Prabhat provides a comprehensive

Building a Finance Agent with LlamaIndex 🦙 🏦🤖

This is a cool mini-blog post by Hanane Dupouy which gives you a finance tool suite to ask questions over public companies:
1. Look up the stock price and last stock prices
2. Search the latest financial news + summarize

We all want mobility rights.
62% of us want to #RejoinEU .
Where is the leadership in our politics for redressing the worst mistake in our history since (at least) 1914?

Is Synthetic Data a Reliable Option for Training #MachineLearning Models?

buff.ly/4cBoBEX v/ Open Data Science

#AI #DataScience
Cc Kirk Borne Terence Mills Eveline Ruehlin AI Harold Sinnott 📲 Yann Marchand

Oct. 2023 ICCV Paris' computer vision event top papers, general trends & personal picks

buff.ly/3FHR9gD v/ AI Summer
#AI #MachineLearning #DeepLearning
Cc Brian Ahier Dion Hinchcliffe AI

Reinforcement Learning, Part 4

The Walking #Robot Problem

buff.ly/48DMetQ MATLAB MathWorks

#AI #MachineLearning #DeepLearning
Cc Spiros Margaris AI Nicolas Babin Jean-Baptiste Lefevre Jean CAYEUX IT 🇫🇷 Fernanda K O Palermo

How chasing #AI

shifts tech #spending patterns

siliconangle.com/2024/04/20/cha… #fintech #ArtificialIntelligence #MachineLearning #GenerativeAI #GenAI Dave Vellante SiliconANGLE

AI Theodora (Theo) Lau - 劉䂀曼 🌻 Harold Sinnott 📲 Dio Favatas Maria Fariello 💙 #TechForGood 💙 Nicolas Babin Joe McKendrick

Arena ELO graph updated with new models.

Llama 3 70b looks impressive, but the 8b Instruct version is pure madness: it outperforms GPT-3.5, Claude 2, and Mistral Medium.

High variance at the moment because not a lot of votes, but interesting to see how it evolves.

(Sorry I

Llama Large Language Models have been helping advance the Open Source Generative #AI LLM community.

Great to see Llama 3 arrive.