Swinburne University of Technology

Amir Aryani

Integrating Large Language Models (LLMs) such as GPT into organizations’ data workflows is a complex process with various challenges. These obstacles include but are not limited to technical, operational, ethical, and legal dimensions, each presenting hurdles that organisations must navigate to harness the full potential of LLMs effectively.

What are the challenges in integrating LLMs into organisations' data workflows?

I asked Generative AI Models about their context window. Their response was intriguing. The context window for a large language model (LLM) like OpenAI’s GPT refers to the maximum amount of text the model can consider at any one time when generating a response. This includes both the prompt provided by the user and the model’s generated text.

What is your Context Window?

Authors: Hui Yin, Amir Aryani  As we discussed in our previous article “A Brief Introduction to Retrieval Augmented Generation (RAG)”, RAG is an artificial intelligence framework that incorporates the latest reliable external knowledge and aims to improve the quality of responses generated by pre-trained language models (PLM). Initially, it was designed to improve the performance of knowledge-intensive NLP tasks (Lewis et al., 2020). As

Navigating the Present: Exploring Practical Horizons of Retrieval-Augmented Generation (RAG)

At the time of writing this post (November 19, 2023), there are 401,014 models and transformers listed on Huggingface.co. This number is a testament to the success and impact of the open-source model in the development of AI technologies. However, the challenge at hand is understanding the available models and keeping up to date with the latest developments.

Estimated time: 12 Years to Review all 400k Models on Hugging Face

Prompt engineering is a technique used to effectively communicate with large language models (LLM) like GPT-3 or GPT-4 and get the desired output. Here there are applications of 8 distinct prompt techniques to interact with Mistral AI and find out how we can prompt effectively to learn about Foundation Models.
<strong>
 Zero-Shot Learning
</strong>
: This involves giving the AI a task without any prior examples.

8 Types of Prompt Engineering

There is a plethora of articles and predictions about the future development of AI. Reading through them suggests three main areas of high-impact changes that would transform our daily lives: Healthcare, Automation, and Manufacturing. The impact of AI in these industries is profound and multifaceted, with each sector experiencing unique transformations. Some of these ideas are described in this NVIDIA article by Cliff Edwards.

Revolutionizing Wellness and Wheels: AI’s Transformative Role in Health and Automotive Industries

Procrastination, a common adversary in our daily lives, often leads to a backlog of tasks and ambitions. It’s a silent thief, stealthily stealing opportunities and time. You might have a stack of books on your bookshelf, longing to be read. Perhaps there’s a new language you’ve wanted to learn, or piles of paperwork cluttering your office that you’ve been meaning to organize.

Maximizing Productivity in 10-Minute Bursts

Authors: Hui Yin , Amir Aryani  With the increasing application of large language models in various scenarios, people realize that these models are not omnipotent. When generating dialogues (Shuster et al., 2021), the models often produce hallucinations, leading to inaccurate answers.

A Brief Introduction to Retrieval Augmented Generation (RAG)

Stories by Amir Aryani on Medium

<figure>
<img
src="https://cdn-images-1.medium.com/max/1024/1*0a6alXzwtqaunJ8K7eE0FA.png" />
</figure>

At the time of writing this post (November 19, 2023), there are 401,014
models and transformers listed on
[Huggingface.co](https://huggingface.co/models). This number is a
testament to the success and impact of the open-source model in the
development of AI technologies. However, the challenge at hand is
understanding the available models and keeping up to date with the
latest developments.

A very rough estimate of the time it might take a person to review all
of these models suggests that it would take more than 12 years to go
through all of the models listed on Hugging Face as of November 2023.

### Time Estimation

Estimating the time it takes for a human to read the description of a
single model on Hugging Face involves several factors, including the
length of the description, the complexity of the content, and the
reading speed of the individual. Here's a breakdown of how to estimate
this time:

1\. **Average Reading Speed**: The average adult reads at about 200--250
words per minute (WPM). However, technical content, like descriptions of
machine learning models, might be read more slowly due to complexity.

2\. **Length of the Description**: The length of model descriptions on
Hugging Face can vary significantly. Some are brief, while others are
quite detailed.

3\. **Complexity of the Content**: Descriptions of machine learning
models often include technical terms and concepts that can slow down
reading speed. A safe estimate might be to assume a reading speed closer
to 150--200 WPM for such content.

This is a rough estimate and can vary based on the individual's
familiarity with the content and their reading speed. Also, some models
have substantial text such as Whisper-large-v3 which includes more than
1,500 words, while Suno Bark includes about 700 words. We take the
estimate of 1,000 per page.

Time to read a model description page = 1,000 words / 150 WPM , which is
approximately 6.6 minutes

Time to read all model descriptions, assuming a 7-hour workday (30
days/month) and no rest for our enthusiastic learner would be 158
months. This is more than 12 years.

    n = 400,000 #Number of Models
    m = 6.6 #Minute per Model
    T = 12,600 #Working Minute per Month (60 X 7 X 30)
    total_working_months = n X m / T # 158.73
    print(total_working_months)

    > 158.73

### Summary

While I do not believe this analysis accurately represents the effort,
value, and contribution of the open-source community to AI development,
it does provide an indication of the vast capabilities in this space.
However, it's worth acknowledging that this estimate may be hindered by
an oversimplification of the effort required to understand the intrinsic
details of each model. Additionally, it overlooks the fact that many of
these models are fine-tuned from the same foundation, exhibiting
substantial similarities.

![](https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=5b9b5b89bc17){width="1"
height="1"}
