Tag: LLM

Create a Clone of Yourself With a Fine-tuned LLM

This article aims to illustrate how to fine-tune a top-performing LLM efficiently and cost-effectively on a custom dataset. We will explore the utilization of the Falcon-7B model with LoRA adapters using Lit-GPT. Ever wondered what it would be like to have a digital twin? A virtual replica o...

Create a Clone of Yourself With a Fine-tuned LLM

This article aims to illustrate how to fine-tune a top-performing LLM efficiently and cost-effectively on a custom dataset. We will explore the utilization of the Falcon-7B model with LoRA adapters using Lit-GPT. Ever wondered what it would be like to have a digital twin? A virtual replica o...

Your Personal Copy Editor Build a LLM-backed App Using LangChain.js and Electron

Using JavaScript to write an LLM-backed app, sounds crazy, no? There are indeed benefits to using JavaScript over Python for apps that heavily depend on external APIs and libraries like LangChain. In the conventional web app model, you’re required to develop an HTML/CSS/JS front-end and a back...

A complete guide to running local LLM models

Meta just released Llama 2 [1], a large language model (LLM) that allows free research and commercial use. It’s expected to spark another wave of local LLMs that are fine-tuned based on it. The open-source community has been very active in trying to build open and locally accessible LLMs as...

FinGPT: open-source LLM for finance

The transformer has changed artificial intelligence, and today the number of LLMs has increased almost exponentially in the past two years, making it almost difficult to keep up. While LLMs are profitably used for various applications, why not apply them to finance as well? Speak about money...

10 things to know before starting to work with Open source LLM — part 1

AI hype is officially up. The release of ChatGPT3 from OpenAI moved the focus on the capabilities of Generative Language Models, and in general to the Artificial Intelligence community. There are a lot communities and platform that hosts Large Language Models (from now on LLM), some are free, man...

Private GPT: Fine-Tune LLM on Enterprise Data

Introduction In the era of big data and advanced artificial intelligence, language models have emerged as formidable tools capable of processing and generating human-like text. Large Language Models like ChatGPT are general-purpose bots capable of having conversations on many topics. However, LLM...

AdventureGPT: Using LLM Backed Agents to Play Text-Based Adventure Games

Recently, I decided to take some time to learn how to utilize ChatGPT and other OpenAI models. Like much of the world, I had played with OpenAI’s chat interface and had some interesting and silly conversations with ChatGPT. However, I wanted to dig deeper and really understand the development ...

FinGPT: open-source LLM for finance

The transformer has changed artificial intelligence, and today the number of LLMs has increased almost exponentially in the past two years, making it almost difficult to keep up. While LLMs are profitably used for various applications, why not apply them to finance as well? Speak about money...

Create a Clone of Yourself With a Fine-tuned LLM

This article aims to illustrate how to fine-tune a top-performing LLM efficiently and cost-effectively on a custom dataset. We will explore the utilization of the Falcon-7B model with LoRA adapters using Lit-GPT. Ever wondered what it would be like to have a digital twin? A virtual replica o...

Building Production-Ready LLM Apps With LlamaIndex: Recursive Document Agents for Dynamic Retrieval

Let’s continue our exploration on building production-ready LLM apps with LlamaIndex. This time let’s focus on recursive document agents, developed by LlamaIndex co-founder and CEO Jerry Liu. Recursive Document Agent We explored data agent in our previous article Low-Code...

Create a Clone of Yourself With a Fine-tuned LLM

This article aims to illustrate how to fine-tune a top-performing LLM efficiently and cost-effectively on a custom dataset. We will explore the utilization of the Falcon-7B model with LoRA adapters using Lit-GPT. Ever wondered what it would be like to have a digital twin? A virtual replica o...

10 things to know before starting to work with Open source LLM — part 1

AI hype is officially up. The release of ChatGPT3 from OpenAI moved the focus on the capabilities of Generative Language Models, and in general to the Artificial Intelligence community. There are a lot communities and platform that hosts Large Language Models (from now on LLM), some are free, man...

All You Need to Know to Build Your First LLM App

If you are just looking for a short tutorial that explains how to build a simple LLM application, you can skip to section “6. Creating a Vector store”, there you have all the code snippets you need to build up a minimalistic LLM app with vector store, prompt template and LLM call. ...

The Power of OpenAI’s Function Calling in Language Learning Models: A Comprehensive Guide

The exciting world of AI has taken another leap forward by the introduction of function calling capabilities in OpenAI’s latest Large Language Models (LLMs). This new feature enhances the interaction between humans and AI, transforming it from a simple question-and-answer format to a more dyna...

Creating a (mostly) Autonomous HR Assistant with ChatGPT and LangChain’s Agents and Tools

OpenAI recently released a paper comparing two training methods aimed at improving the reliability of Large Language Models (LLM): model training by ‘process supervision’ and model training by ‘outcome supervision’. Essentially, one model is rewarded for the ...

Compute without Constraints: Serverless GPU + LLM = Endless Possibilities

For developers working with large language models, the constraints of hardware can often hold back the boundaries of what’s possible. In fact securing access to GPUs requires a lot of upfront investment and technical overhead. For developers working with large language models, the constrain...

Platypus: Quick, Cheap, and Powerful LLM

In recent years, model parameters have exploded to a huge number of parameters (540 B with PaLM). The question that has been asked is whether this number of parameters is necessary. According to OpenAI, as models grow, there is an increase in performance. In addition, there is the appearance of e...

A Beginner’s Guide to LLM Fine-Tuning

The growing interest in Large Language Models (LLMs) has led to a surge in tools and wrappers designed to streamline their training process. Popular options include FastChat from LMSYS (used to train Vicuna) and Hugging Face’s transformers/trl libraries (used i...

RAG vs Fine-Tuning: Choosing the Best Tool for Your LLM

In the ever-evolving world of machine learning, choosing the right tool can sometimes feel like finding a needle in a haystack. Today, we’re diving deep into two popular approaches when working with large language models like GPT-4: RAG (Retrieval-Augmented Generation) and fine-tuning. Grab a ...

A complete guide to running local LLM models

Meta just released Llama 2 [1], a large language model (LLM) that allows free research and commercial use. It’s expected to spark another wave of local LLMs that are fine-tuned based on it. The open-source community has been very active in trying to build open and locally accessible LLMs as...

Private GPT: Fine-Tune LLM on Enterprise Data

In the era of big data and advanced artificial intelligence, language models have emerged as formidable tools capable of processing and generating human-like text. Large Language Models like ChatGPT are general-purpose bots capable of having conversations on many topics. However, LLMs can also be fi...

Your Fate in Robopsychologists’ Hands

Once upon a time, humans gazed at the stars and pondered what existed beyond our planet’s borders. Now, as we peer into the digital universe, we find ourselves asking a similar question: what mysteries lie within the depths of artificial intelligence… and what dangers? The key to und...

Everyone’s Getting Ghosted

The company I interviewed for was up and coming, YC funded, now profitable, a well-known player in the generative AI space. I was excited for the opportunity. They have many in-house recruiting resources and a policy to not ghost candidates. Yet, I got ghosted. I’m not alone in this,...

Fine-tuning Llama 2 for news category prediction: A step-by-step comprehensive guide to fine-tuning any LLM (Part 1)

In this blog, I will guide you through the process of fine-tuning Meta’s Llama 2 7B model for news article categorization across 18 different categories. I will utilize a news classification instruction dataset that I previously created using GPT 3.5. If you’re interested ...

RAG vs Finetuning — Which Is the Best Tool to Boost Your LLM Application?

As the wave of interest in Large Language Models (LLMs) surges, many developers and organisations are busy building applications harnessing their power. However, when the pre-trained LLMs out of the box don’t perform as expected or hoped, the question on how to improve the performance of the L...

Platypus: Quick, Cheap, and Powerful LLM

A family of finetuned and merged models that reached the top positions of the Open LLM Leaderboard. How did they do it? How to reduce the cost of your model? Photo by Alexander Mils on Unsplash In recent years, model parameters have exploded to a huge number of parameters...

A Beginner’s Guide to LLM Fine-Tuning

The growing interest in Large Language Models (LLMs) has led to a surge in tools and wrappers designed to streamline their training process. Popular options include FastChat from LMSYS (used to train Vicuna) and Hugging Face’s transformers/trl libraries (used i...

Pydantic and Prompt Engineering: The Essentials for Validating Language Model Outputs

Large language models (LLMs) output text in reaction to our prompts. While this provides a satisfactory interaction when chatting with them, it poses a challenge when we aim to incorporate these models into our applications. For a seamless integration, it is often crucial to have these responses in ...

Large Language Models, Part 1: BERT

2017was a historical year in machine learning when the Transformer model made its first appearance on the scene. It has been performing amazingly on many benchmarks and has become suitable for lots of problems in Data Science. Thanks to its efficient architecture, many other Transformer-ba...

RAG vs Fine-Tuning: Choosing the Best Tool for Your LLM

In the ever-evolving world of machine learning, choosing the right tool can sometimes feel like finding a needle in a haystack. Today, we’re diving deep into two popular approaches when working with large language models like GPT-4: RAG (Retrieval-Augmented Generation) and fine-tuning. Grab a ...

Fine tuning Falcon 180B LLM Model

In the ever-evolving landscape of generative artificial intelligence, a new player has emerged, ready to make its mark and redefine the boundaries of what’s possible. Today, we are thrilled to introduce you to TII’s Falcon 180B, a ground-breaking achievement in the world of ope...

A complete guide to running local LLM models

Meta just released Llama 2 [1], a large language model (LLM) that allows free research and commercial use. It’s expected to spark another wave of local LLMs that are fine-tuned based on it. The open-source community has been very active in trying to build open and locally accessible LLMs as...

Private GPT: Fine-Tune LLM on Enterprise Data

In the era of big data and advanced artificial intelligence, language models have emerged as formidable tools capable of processing and generating human-like text. Large Language Models like ChatGPT are general-purpose bots capable of having conversations on many topics. However, LLMs can also be fi...

Fine Tuning LLM: Parameter Efficient Fine Tuning (PEFT) — LoRA & QLoRA — Part 2

In this blog, we will implement LoRA the idea behind Parameter Efficient Fine Tuning (PEFT), and explore LoRA and QLoRA, Two of the most important PEFT methods. We will also be exploring “Weights and Biases” for capturing the training metrics. We will be fine-tuning a small Salesforce co...

7 Ways to Speed Up Inference of Your Hosted LLMs

Companies, from small startups to large corporations, want to utilize the power of modern LLMs and include them in the company’s products and infrastructure. One of the challenges they face is that such large models require a huge number of resources for deployment (inference). Accelerating...

How to Pick the Best LLM for Your AI Project

Feeling overwhelmed by the multitude of LLMs out there? Trust me, you’re not alone. Faced with choices from giants like OpenAI, Google, and Anthropic, plus a heap of open-source options, you don’t really know where to start. Worse still you’re concerned about the restrictions that ...

A Very Gentle Introduction to Large Language Models without the Hype

This article is designed to give people with no computer science background some insight into how ChatGPT and similar AI systems work (GPT-3, GPT-4, Bing Chat, Bard, etc). ChatGPT is a chatbot — a type of conversational AI built — but on top of a Large Language Model. Those are defi...

Everything You Should Know About Evaluating Large Language Models

As open source language models become more readily available, getting lost in all the options is easy. How do we determine their performance and compare them? And how can we confidently say that one model is better than another? This article provides some answers by presenting training and eva...

ChatGPT, Random Numbers, and the Lottery

A couple of months ago, there were major news headlines on how people won the lottery by asking ChatGPT to guess the winning numbers. Although they were not able to win the jackpot, they certainly won something in the neighborhood of $40, which is still pretty cool. With all the hype, I was natur...

Large Language Models in Molecular Biology

Will we ever decipher the language of molecular biology? Here, I argue that we are just a few years away from having accurate in silico models of the primary biomolecular information highway — from DNA to gene expression to proteins — that rival experimental accuracy and can be used in m...

How ChatGPT Works: The Models Behind The Bot

This gentle introduction to the machine learning models that power ChatGPT, will start at the introduction of Large Language Models, dive into the revolutionary self-attention mechanism that enabled GPT-3 to be trained, and then burrow into Reinforcement Learning From Human Feedback, the novel techn...

A comprehensive and hands-on guide to autonomous agents with GPT

Every time I think the pace of advancement in GPT is fast, it gets even faster. In the past month, the concept of GPT/LLM-backed autonomous agents is getting wild — with AutoGPT, the most famous project in this area, getting over 117K stars on GitHub in less than a month since its release and ...

2D Tokenization for Large Language Models

When passing text to a Large Language Model (LLM), text is broken down into a sequence of words and sub-words. This sequence of tokens is then replaced with a sequence of integers and passed to the model. LLMs contain an embedding matrix to store a representation for each of these tokens. In the ...

The Falcon LLM Landing in the Snowflake Data Cloud

Opinions expressed in this post are solely my own and do not represent the views or opinions of my employer. I am using feature that are in Private Preview at the time of writing. With the launch of Snowpark Container Services in Private Preview, any code or software that can be contain...

10 Exciting Project Ideas Using Large Language Models (LLMs) for Your Portfolio

One common piece of advice I often hear for job applicants is to have a portfolio showcasing your work. This doesn't only apply to artists or models but also to software developers and data scientists. A portfolio of your projects acts as public evidence of your skills. This public evidence c...

Getting Started with LangChain: A Beginner’s Guide to Building LLM-Powered Applications

Since the release of ChatGPT, large language models (LLMs) have gained a lot of popularity. Although you probably don’t have enough money and computational resources to train an LLM from scratch in your basement, you can still use pre-trained LLMs to build something cool, such as: Person...

Prompt Engineering to Leverage In-Context Learning in Large Language Models

Large Language Models are more and more used and their skills are surprising. Part of their success is their ability to learn from a few examples, a phenomenon known as in-context learning; in the previous article, we discussed in detail what is it and from where it originates, now we will...

AI: RAG vs Fine-tuning — Which Is the Best Tool to Boost Your LLM Application?

Choosing between Retrieval-Augmented Generation (RAG) and fine-tuning is crucial for building effective large language model applications. Though both techniques boost model capabilities, they optimize different objectives under varying constraints. Fine-tuning adapts the entire model throug...

DAY 5 OF THE LLM EXPERIMENTS

I am sort of sticking this in to the end of my day, like a rushed cup of coffee or push ups and sit ups between meetings. But each experiment i do teaches me something new — to make a truly banal comment. I am thinking about creating a format for these writeups so they are less idiosycratic...

Is Hosting Your Own LLM Cheaper than OpenAI? Hint: It Could Be

Open AI Pricing Open AI charges per token. 750 words are approximately 1000 tokens. The price per token also depends on the model. For e.g., GPT-4 (new) costs $0.03 (3 cents) per 1000 tokens GPT-3.5 (older) costs $0.0015 (.15 cents) per 1000 tokens. Now, let’s see this prici...

LLM Economics: ChatGPT vs Open-Source

TLDR: For lower usage in the 1000’s of requests per day range ChatGPT works out cheaper than using open-sourced LLMs deployed to AWS. For millions of requests per day, open-sourced models deployed in AWS work out cheaper. (As of writing this article on April 24th, 2023.) Large Lan...

Databricks introduces a public preview of GPU and LLM optimization support for Databricks Model Serving

Main AI News: Databricks has unveiled its latest innovation: the public preview of GPU and LLM optimization support for Databricks Model Serving. This transformative feature empowers users to effortlessly deploy a diverse array of AI models, including LLMs and Vision models, directly onto the Lak...

Navigating the World of Chatbots with LLM Evaluation: A Databricks Case Study

Hello…there! Chatbots have become an integral part of our digital interactions, and they owe their prowess to Large Language Models (LLMs). One cutting-edge approach in chatbot development is the Retrieval Augmented Generation (RAG) architecture. It combines the best of both worlds: know...