Rere

"90% of the time, it actually is rocket science." Machine Learning/Data Mining Researcher/Spiritual Seekers

[elvis @omarsar0]

Create Your Own Custom LLM Chatbot

Impressive step-by-step tutorial explaining how to choose the best LLM and the components needed for building your own custom LLM-powered chatbot.

@abacusai offers one of the best solutions that I've used to quickly build custom LLM chatbots.

The foundational parts discussed in the tutorial are:

�� Data sources - data warehouses, data lakes, and a range of databases are supported. You can also transform data within the platform as needed. There is even an AI agent that can assist with operating on data.

• Chunk size - the chunk size determines how to split the text; this affects performance and varies by use case. You should also think about the overlap between adjacent chunks so information is not abruptly cut off.

• Embedding technique and document retriever - the chunks of texts are embedded and stored in a vector database that helps you build a powerful retriever that the LLM interacts with to ensure it's using the relevant information to answer questions. This is particularly useful for a lot of knowledge-intensive use cases.

• LLM - the synthesizing capabilities of LLMs combined with the retrievers enables a robust solution to create your custom LLM chatbots and pick the best LLM for your dataset and task. With @abacusai you can choose between models offered by Google, OpenAI, Anthropic, the open-source community, and Abacus's proprietary LLMs. I like that you can also fine-tune your own models as well so the offering is pretty comprehensive.

• Automation and Evaluation - picking the right model and the right configurations is challenging. The AutoML capabilities of Abacus help in this regard. You can also upload an evaluation dataset that enables the platform to compare combinations and determine an optimal solution for your use case. Metrics include BLEU score, METEOR, and others.

• Deployment & Monitoring - this whole process is iterative in nature and new data will always be available. You can deploy your LLMs and set up pipelines to keep incorporating or fine-tuning on new data. Having your solution in production means you need to continuously evaluate and monitor performance on a regular basis to ensure the solution doesn't deteriorate.

Read more here: https://t.co/WcQEbqtAZa

If there is enough interest, I will also be posting a full demo with a use case in an upcoming post. Stay tuned!

[Python Coding @clcoding]

What is the output of the following Python code?

[elvis @omarsar0]

This maths book is trending on Hacker News!

I took a quick look and realized how great of a book this is to learn how to think mathematically.

It's 700 pages long and very approachable compared to other maths books.

https://t.co/Ra2EtO3ET9

[Akshay 🚀 @akshay_pachaar]

Two of the fundamental evaluation metrics in machine learning are:

- Precision
- Recall

But, their formal definitions can be a bit confusing.

Today, I'll clearly explain precision & recall using illustrative examples! 🚀

A Thread 🧵👇

[Towards Data Science @TDataScience]

If you're taking your first steps in machine learning and need some guidance on how to approach logistic regression, don't miss @roiyeho's thorough (hands-on) introduction. https://t.co/OyclFq1xu0

[Kirk Borne @KirkDBorne]

Tiny #Python Projects — 21 small fun projects for Python beginners designed to build programming skill, teach new algorithms and techniques: https://t.co/dl40lMvP1l
————
#Coding #BigData #DataScience #AI #MachineLearning #DataScientists #100DaysOfCode

[Mark Riedl @mark_riedl]

My online NLP course is kicking off Monday morning 😱

All lectures written and recorded from scratch. All new programming assignments written from scratch. It's taken me a year.

[Python Developer @PythonDvz]

Introduction to Web Development in Python and Django
#python #django
https://t.co/2fcGboRTnp

[Python Coding @clcoding]

Free Web Scraping using Python https://t.co/yc9QdUNv2k

[Swapna Kumar Panda @swapnakpanda]

Learn Data Science, Earn Certificate
**ALL FREE**

❯ Python
https://t.co/9OSnj5oOxF

❯ SQL
https://t.co/OyFZOvLGHk

❯ Excel
https://t.co/lhoeQTlfRY

❯ PowerBI
https://t.co/PxucoibnGR

❯ Tableau
https://t.co/PFz80W7Cg9

❯ Mathematics (Statistics)
matlabacademy.mathworks. com

❯ Data Analysis
https://t.co/RNcQyU9kUS

❯ Data Visualization
https://t.co/SmkcXww0GI

❯ Data Cleaning
https://t.co/h8bKUmaUO9

❯ Machine Learning
https://t.co/jA8ZFAGhc2

❯ Deep Learning
https://t.co/a8jOtbXmyK

[Job Corner @JOBCORNER247]

INTERVIEW TIPS:

These Interview tips could be helpful to somebody out there so please share them.

#tips #interview

[Cardio Arena @CadioArena]

Easy Exercises That Will Transform Your Body in 4 Weeks

[Gabriel Peyré @gabrielpeyre]

The binomial law is a sum of Bernoulli 0/1 random variables. After rescaling, converge to a Gaussian for a large number of variables (a particular case of the central limit theorem). https://t.co/oCWKqBInAd

[Towards Data Science @TDataScience]

Learn the math and methods behind the libraries you use daily as a data scientist with Adrienne Kline's post. https://t.co/Ia3qLAKLom

[PyQuant News 🐍 @pyquantnews]

During my master's degree, I read 65 books on quant finance.

Most of them were useless.

But these 4 are still on my shelf 10 years later.

And they should be on yours too:

[Mindset Machine  @mindsetmachine]

25 Things About Life I Wish I Had Known 10 Years Ago...

[Swapna Kumar Panda @swapnakpanda]

ChatGPT is phenomenal. But you'll excel only when you understand it.

Learn AI for FREE.

❯ Intro to AI
https://t.co/VNVd5pGZZt

❯ AI for everyone
https://t.co/6AUVa3NMu3

❯ Introduction to AI with Python
https://t.co/1DjuefW5BO

❯ Intro to Machine Learning
https://t.co/mZMAS5bxkK

❯ Learn AI Basics
https://t.co/isR3P2I7KM

❯ ChatGPT 101
https://t.co/1O8xgAe7fY

❯ ChatGPT for Beginners
https://t.co/E2dmnkOSVp

❯ AI Projects
https://t.co/ohi1uQwrYU

❯ Build your own Chatbot
https://t.co/GxxcbuKyTj

[Jas Singh @TheJasSingh]

ChatGPT was good.

But, ChatGPT with plug-ins is even better.

Here's a list of 7 Plug-ins & their use cases (All new):