Tag: LLMs

Speech and Natural Language Input for Your Mobile App Using LLMs

A Large Language Model (LLM) is a machine learning system that can effectively process natural language. The most advanced LLM available at the moment is GPT-4, which powers the paid version of ChatGPT. In this article you will learn how to give your app highly flexible speech interpretation using G...

7 Frameworks for Serving LLMs

While browsing through LinkedIn, I came across a comment that made me realize the need to write a simple yet insightful article to shed light on this matter: “Despite the hype, I couldn’t find a straightforward MLOps engineer who could explain how we can deploy these open-source mod...

GPTQ or bitsandbytes: Which Quantization Method to Use for LLMs — Examples with Llama 2

As large language models (LLM) got bigger with more and more parameters, new techniques to reduce their memory usage have also been proposed. One of the most effective methods to reduce the model size in memory is quantization. You can see quantization as a compression technique for LLMs. In...

Steering LLMs with Prompt Engineering

Large Language Models (LLMs) have captured our attention and imagination in the past six months since the announcement of ChatGPT. However, LLMs’ behaviors are often stochastic in nature, making it difficult for them to be integrated into a business application with well-defined limits. In thi...

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...

Fixing Hallucinations in LLMs

Generative Large Language Models (LLMs) can generate highly fluent responses to various user prompts. However, their tendency to hallucinate or make non-factual statements can compromise trust. I think we will get the hallucination problem to a much, much better place… it will take us a ...

Parameter-Efficient Fine-Tuning (PEFT) for LLMs: A Comprehensive Introduction

Large Language Models (LLMs) are quite large by name. These models usually have anywhere from 7 to 70 billion parameters. To load a 70 billion parameter model in full precision would require 280 GB of GPU memory! To train that model you would update billions of tokens over millions or billions of do...

Prompt Ensembles Make LLMs More Reliable

Anyone who has worked with large language models (LLMs) will know that prompt engineering is an informal and difficult process. Small changes to a prompt can cause massive changes to the model’s output, it is difficult (or even impossible in some cases) to know the impact that changing a promp...

Speech and Natural Language Input for Your Mobile App Using LLMs

Introduction A Large Language Model (LLM) is a machine learning system that can effectively process natural language. The most advanced LLM available at the moment is GPT-4, which powers the paid version of ChatGPT. In this article you will learn how to give your app highly flexible speech interp...

12 things I wish I knew before starting to work with Hugging Face LLM

Hugging Face has become one of the most popular open-source libraries for Artificial Intelligence. It is a treasure for every enthusiast of Natural Language Processing tasks. When you access the Hugging Face’s Language Model Hub you are in a complete new world of possibilities. I star...

Integrating Knowledge Graphs with Large Language Models for More Human-like AI Reasoning

Reasoning — the ability to think logically and make inferences from knowledge — is integral to human intelligence. As we progress towards developing artificial general intelligence, reasoning remains a core challenge for AI systems. While large language models (LLMs) like GPT-3 exhibi...

Can We Stop LLMs from Hallucinating?

While Large Language Models (LLMs) have captured the attention of nearly everyone, wide-scale deployment of such technology is slightly limited due to a rather annoying aspect of it — these models tend to hallucinate. In simple terms, they sometimes just make things up, and worst of all, it of...

You don’t need hosted LLMs, do you?

During the LLM hype, you can find a lot of articles like “Fine-tune your Private LLaMA/Falcon/Another Popular LLM”, “Train Your Own Private ChatGPT”, “How to Create a Local LLM” and others. At the same time, only few people tell why you need it. I mean, ar...

Speech and Natural Language Input for Your Mobile App Using LLMs

The Future of LLMs is Here! Discover LangChain and Gorilla-Cli(and Start Using Them Today)

In the digital era, large language models (LLMs) have transformed how we interact with technology, offering human-like text generation, answering queries, and aiding in tasks like coding. Their versatility has led to widespread adoption in fields from customer service to content creation. Despite...

Natural Language Processing For Absolute Beginners

It is mostly true that NLP (Natural Language Processing) is a complex area of computer science. Frameworks like SpaCy or NLTK are large and often require some learning. But with the help of open-source large language models (LLMs) and modern Python libraries, many tasks can be solved much more easil...

The Future of Storytelling: Creating Compelling Photo-to-Audio Narratives with free AI

We are surrounded by AI models and tools: it is better to say that for the one of us that are following the evolution of LLMs we are almost overloaded. But don’t you feel that we are left behind? Big companies and tools are hidden behind black boxes, and we are not entitled to understand ho...

Safeguarding LLMs with Guardrails

As the use of large language model (LLM) applications enters the mainstream and expands into larger enterprises, there is a distinct need to establish effective governance of productionized applications. Given that the open-ended nature of LLM-driven applications can produce responses that may not a...

Can We Stop LLMs from Hallucinating?

Parameter-Efficient Fine-Tuning (PEFT) for LLMs: A Comprehensive Introduction

GPTQ or bitsandbytes: Which Quantization Method to Use for LLMs — Examples with Llama 2

7 Frameworks for Serving LLMs

3 Ways to Not Let AI Take Your Job

You are worried that AI is becoming insanely smart and is coming to change everything and take your six figure tech job away, and you are wondering what kind of skills you should focus on learning in order to position yourself well for that new world — this article is for you. Let’s get ...

Where Are All the Women?

Large language models (LLMs) such as ChatGPT are being increasingly used in educational and professional settings. It is important to understand and study the many biases present in such models before integrating them into existing applications and our daily lives. One of the biases I studied in ...

Fixing Hallucinations in LLMs

Fine-tuning LLMs

Catastrophic Forgetting (degrades model performance) Catastrophic forgetting occurs when a machine learning model forgets previously learned information as it learns new information. This process is especially problematic in sequential learning scenarios where the model is trained on multiple ...

The Secret Sauce behind 100K context window in LLMs: all tricks in one place

tldr; techniques to speed up training and inference of LLMs to use large context window up to 100K input tokens during training and inference: ALiBi positional embedding, Sparse Attention, FlashAttention, Multi-Query attention, Conditional computation, and 80GB A100 GPUs. Recently there ...

Steering LLMs with Prompt Engineering

DLite V2: Lightweight, Open LLMs That Can Run Anywhere

AI Squared is committed to democratizing AI so that it can be used by all. There are two key forces opposing the democratization of AI though — a tendency for high-performing models to have a huge number of parameters, making them incredibly expensive to train, tune, and deploy at scale &mdash...

Three mistakes when introducing embeddings and vector search

Representing unstructured data as embedding vectors and embedding-based retrieval (EBR) using vector search is more popular than ever. What are embeddings anyway? Roy Keyes explains it well in The shortest definition of embeddings? Embeddings are learned transformations to make data more u...

Applying LLMs to Enterprise Data: Concepts, Concerns, and Hot-Takes

Ask GPT-4 to prove there are infinite prime numbers — while rhyming — and it delivers. But ask it how your team performed vs plan last quarter, and it will fail miserably. This illustrates a fundamental challenge of large language models (“LLMs”): they have a good grasp ...

Generative AI - Document Retrieval and Question Answering with LLMs

With Large Language Models (LLMs), we can integrate domain-specific data to answer questions. This is especially useful for data unavailable to the model during its initial training, like a company's internal documentation or knowledge base. The architecture is called Retrieval Augmentat...

Forget 32K of GPT4: LongNet Has a Billion Token Context

On 19th July, Microsoft published a paper that is being considered as a major step forward in the development of architectures to develop large language models that could have a practically unlimited context length. Microsoft proposed and developed a transformer model that can scale to theoretically...

There are no emergent abilities in LLMs

The 2022 paper titled “Emergent Abilities of Large Language Models” [1] has been the source of much speculation — and much hysteria — about the future of AI [2], [3]. The paper’s central claim is that large language models (LLMs) display “emergent abilities”...

Build Industry-Specific LLMs Using Retrieval Augmented Generation

In the Microsoft Build session Vector Search Isn’t Enough, they lay out their product that combines less context-aware LLMs with vector search, to create a more engaging experience. The talk starts from the opposite direction of this piece — from the point of view of Elastic Sear...

Multi-step multi-PDF Q&A system with LLMs and Langchain

Hello folks! The topic of this particular blog post will not be unique at the moment of writing. There are already many YouTube videos, articles, and Twitter threads that describe this idea of talking to PDFs. There are chat GPT plugins that can do this, and there is Langchain, a library that allows...

Train Instruct LLMs On Your GPU with DeepSpeed Chat — Step #1: Supervised Fine-tuning

Instruct large language models (LLMs) have become extremely popular since the release of ChatGPT by OpenAI. We can now find online many chat models mimicking the behavior of ChatGPT (since many of them are actually trained on ChatGPT’s outputs) and fine-tuned for different domains. OpenAI d...

Document-Oriented Agents: A Journey with Vector Databases, LLMs, Langchain, FastAPI, and Docker

Document-oriented agents are starting to get traction in the business landscape. Companies increasingly leverage these tools to capitalize on internal documentation, enhancing their business processes. A recent McKinsey report [1] underscores this trend, suggesting generative AI could boost the glob...

Comparing LLMs with MLFlow

Comparing models is just as important in Large Language Model Ops (LLMOps) as it is in MLOps, but the process for doing so is a little less clear. In “classical” machine learning, it usually suffices to compare models on a set of clear numerical metrics; the model with the better score w...

Harness The Power of LLMs: How to extract data from legacy documents using LLMs

Legacy documents represent a treasure trove of historical records, institutional knowledge, and critical insights that organizations often rely on for decision-making, compliance, and historical research. However, as technology advances and document formats change, these invaluable resources risk be...

Will AI Replace Lawyers? Research on the Application of LLMs in the Legal Field

Recently, there has been a shift in investment focus in the primary market from the field of LLMs to the application layer of large language models. There is a growing focus on how to effectively integrate large language models into practical scenarios. In various applications, we see great potentia...

What We Can Expect In 2024 With LLMs

In a world where timely diagnosis can mean the difference between life and death, LLMs are emerging as invaluable assistants. While they don’t replace human medical professionals, they do provide a supplementary layer of support. Example: An AI-driven chatbot, powered by an LLM, can convers...

Leveraging LLMs with LangChain for Supply Chain Analytics — A Control Tower Powered by GPT

A Supply Chain Control Tower can be defined as a centralized solution that provides visibility and monitoring capabilities to manage end-to-end supply chain operations efficiently. This analytical tool enables a Supply Chain department to track, understand and resolve critical issues in real time...

Custom LLMs in Action: How to successfully integrate LLMs in your company

Welcome to the first post of our series “Custom LLMs in Action”, which aims to guide businesses through the complex process of integration of LLMs in their operations by leveraging Aptitude’s first hand experience. Throughout this series we will delve into various perspectives; str...

LLMs for philosophers (and philosophy for LLMs)

(Edit: as some people are reading this, I figured I’d share some of my academic work on the topic — this is about how to think of meaning when it comes to LLMs. The title is missing, it’s anonymous, and I put it through ChatGPT to help anonymous review but feel free to sh...