Gemini: A Family of Highly Capable Multimodal Models

Claude vs ChatGPT: A Comparison of AI Chatbots

Claude and ChatGPT are two compelling options in AI chatbots, each with unique features and capabilities. To discern their strengths and suitability for various applications, let's compare these two AI chatbots comprehensively. What is Claude? Claude is an AI chatbot developed…

Peter Gostev’s Post

We are seeing some clear categories emerge in the world of LLMs - 1) affordable (~$1 per million tokens); 2) mid-range ($8/m) and 3) top end ($25-50/m)… | 32 comments on LinkedIn

Let's build GPT: from scratch, in code, spelled out. - YouTube

We build a Generatively Pretrained Transformer (GPT), following the paper "Attention is All You Need" and OpenAI's GPT-2 / GPT-3. We talk about connections to ChatGPT, which has taken the world by storm. We watch GitHub Copilot, itself a GPT, help us write a GPT (meta :D!) . I…

DALL-E now lets you edit images in ChatGPT

More AI image generation tools at your fingertips.

Meet RAGFlow: An Open-Source RAG (Retrieval-Augmented Generation) Engine Ba

In the ever-evolving landscape of artificial intelligence, businesses face the perpetual challenge of harnessing vast amounts of unstructured data. Meet RAGFlow, a groundbreaking open-source AI project that promises to revolutionize how companies extract insights and answer…

RAG Step-by-Step: Open Source Edition

In a previous post, I demonstrated how to implement RAG using the Load-Transform-Embed-Store...

Detecting Hallucinations in Large Language Models with Text Similarity Metr

In the world of LLMs, there is a phenomenon known as "hallucinations." These hallucinations are...

Top Open Source Large Language Models (LLMs) Available For Commercial Use

The top open source Large Language Models available for commercial use are as follows. Llama - 2 Meta released Llama 2, a set of pretrained and refined LLMs, along with Llama 2-Chat, a version of Llama 2. These models are scalable up to 70 billion parameters. It was discovered…

LLaMA Now Goes Faster on CPUs

I wrote 84 new matmul kernels to improve llamafile CPU performance.

Large language models use a surprisingly simple mechanism to retrieve some

Researchers find large language models use a simple mechanism to retrieve stored knowledge when they respond to a user prompt. These mechanisms can be leveraged to see what the model knows about different subjects and possibly to correct false information it has stored.

Introducing DBRX: A New State-of-the-Art Open LLM

ChatGPT vs Perplexity AI: AI App Comparison

What is ChatGPT? ChatGPT, developed by OpenAI, is an AI platform renowned for its conversational AI capabilities. Leveraging the power of the Generative Pre-trained Transformer models, ChatGPT generates human-like text responses across various topics, from casual conversations…

Mamba Explained

Is Attention all you need? Mamba, a novel AI model based on State Space Models (SSMs), emerges as a formidable alternative to the widely used Transformer models, addressing their inefficiency in processing long sequences.

How Nvidia Blackwell Systems Attack 1 Trillion Parameter AI Models

We like datacenter compute engines here at The Next Platform, but as the name implies, what we really like are platforms – how compute, storage,

How Chain-of-Thought Reasoning Helps Neural Networks Compute

Large language models do better at solving problems when they show their work. Researchers are beginning to understand why.

Why and How to Achieve Longer Context Windows for LLMs

Language models (LLMs) have revolutionized the field of natural language processing (NLP) over the last few years, achieving…

Generative AI Design Patterns: A Comprehensive Guide | by Vincent Koc | Feb

Reference architecture patterns and mental models for working with Large Language Models (LLM’s)

You can now train a 70b language model at home

We’re releasing an open source system, based on FSDP and QLoRA, that can train a 70b model on two 24GB GPUs.

Easily Train a Specialized LLM: PEFT, LoRA, QLoRA, LLaMA-Adapter, and More

Training a specialized LLM over your own data is easier than you think…

Google Bard is called Gemini now and expands to mobile, paid versions

The search giant is unifying its AI-assistant efforts under one name and trying to show it can match rivals.

Happy New Year: GPT in 500 lines of SQL

A complete GPT2 implementation as a single SQL query in PostgreSQL.

Anthropic’s Post

Today, we're announcing the Claude 3 model family, which sets new industry benchmarks across a wide range of cognitive tasks. The family includes three… | 429 comments on LinkedIn

OpenAI's ChatGPT may have its first true rival in Anthropic's new chatbot

The Amazon-backed AI startup said its "most intelligent model" outperformed OpenAI's powerful GPT-4

WTF are OpenAI’s custom GPTs?

OpenAI's custom GPTs and GPT Store could proffer a potential new platform for publishers to drive referral traffic.

rasbt/LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step - rasbt/LLMs-from-scratch

Meet RAGxplorer: An interactive AI Tool to Support the Building of Retrieva

Understanding how well they comprehend and organize information is crucial in advanced language models. A common challenge arises in visualizing the intricate relationships between different document parts, especially when using complex models like the Retriever-Answer Generator…

Meet Google Lumiere AI, Bard’s video maker cousin

Step into the future of video creation with Google Lumiere, the latest breakthrough from Google Research that promises to redefine

How To Build an LLM-Powered App To Chat with PapersWithCode

Keep up with the latest ML research

Unlocking AI’s Potential: A Comprehensive Survey of Prompt Engineering Tech

Prompt engineering has burgeoned into a pivotal technique for augmenting the capabilities of large language models (LLMs) and vision-language models (VLMs), utilizing task-specific instructions or prompts to amplify model efficacy without altering core model parameters. These…

The killer app of Gemini Pro 1.5 is video

Last week Google introduced Gemini Pro 1.5, an enormous upgrade to their Gemini series of AI models. Gemini Pro 1.5 has a 1,000,000 token context size. This is huge—previously that …

Understanding Direct Preference Optimization

This blog post will look at the “Direct Preference Optimization: Your Language Model is Secretly a Reward Model” paper and its findings.

I Spent a Week With Gemini Pro 1.5—It’s Fantastic

When it comes to context windows, size matters

Attention for Vision Transformers, Explained

The Math and the Code Behind Attention Layers in Computer Vision

Title:The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits

Recent research, such as BitNet, is paving the way for a new era of 1-bit Large Language Models (LLMs). In this work, we introduce a 1-bit LLM variant, namely BitNet b1.58, in which every single...

An Introduction to Prompting for LLMs

How do we communicate effectively with LLMs?

Sora early access: Your guide to securing a spot

Are you looking for the news everyday for Sora early access like us? Well you are absolutely right because OpenAI's

Au Large | Mistral AI | Frontier AI in your hands

Mistral Large is our flagship model, with top-tier reasoning capacities. It is also available on Azure.

17 Tips to Take Your ChatGPT Prompts to the Next Level

Sure, anyone can use OpenAI’s chatbot. But with smart engineering, you can get way more interesting results.

Claude

Talk with Claude, an AI assistant from Anthropic

The Art of Engineering AI Prompts

In the rapidly evolving world of artificial intelligence, the ability to communicate effectively with AI tools has become an indispensable skill. Whether you're generating content, solving complex data problems, or creating stunning digital art, the quality of the outcomes you…

Beyond Self-Attention: How a Small Language Model Predicts the Next Token

A deep dive into the internals of a small transformer model to learn how it turns self-attention calculations into accurate predictions for the next token.

How do transformers work?+Design a Multi-class Sentiment Analysis for Custo

We will deep dive into understanding how transformer model work like BERT(Non-mathematical Explanation of course!). system design to use the transformer to build a Sentiment Analysis

Grokking Groq’s Groqness

Startup Groq has developed an machine learning processor that it claims blows GPUs away in large language model workloads – 10x faster than an Nvidia GPU at 10 percent of the cost, and needing a tenth of the electricity. Update: Groq model compilation time and time from access…

1708022141659 (JPEG Image, 1280 × 1600 pixels) — Scaled (56%)

Groq Inference Tokenomics: Speed, But At What Cost?

Faster than Nvidia? Dissecting the economics

How Well Can LLMs Negotiate? Stanford Researchers Developed ‘NegotiationAre

In artificial intelligence, the capacity of Large Language Models (LLMs) to negotiate mirrors a leap toward achieving human-like interactions in digital negotiations. At the heart of this exploration is the NEGOTIATION ARENA, a pioneering framework devised by researchers from…

Sora

Sora is an AI model that can create realistic and imaginative scenes from text instructions.

Code LoRA from Scratch - a Lightning Studio by sebastian

LoRA (Low-Rank Adaptation) is a popular technique to finetune LLMs more efficiently. This Studio explains how LoRA works by coding it from scratch, which is an excellent exercise for looking under …

Bard is now Gemini and Gemini Advanced is amazing

AI community is once again filled with excitement as Bard is now Gemini and Gemini Advanced offering users an exceptional