AI/ML

Colab: https://colab.research.google.com/drive/1gyGZn_LZNrYXYXa-pltFExbptIe7DAPe?usp=sharing In this video I look at how to load multiple docs into a single Vectors Store retriever and then do QA over all the docs and return their source info along with answers.

As it’s currently imagined, the technology promises to concentrate wealth and disempower workers. Is an alternative possible?

An incomplete list of open-sourced fine-tuned Large Language Models (LLM) you can run locally on your computer

🤖 A list of open LLMs available for commercial use. - eugeneyan/open-llms: 🤖 A list of open LLMs available for commercial use.

As it’s currently imagined, the technology promises to concentrate wealth and disempower workers. Is an alternative possible?

Two OpenAI contractors spoke to NBC News about their work training the system behind ChatGPT.

Imagine a bunch of product managers sitting in a sprint planning meeting where, after signing off on the tasks to be done this sprint and starting the sprint, ChatGPT was deployed on those tasks.

AI startup Hugging Face and ServiceNow teamed up to create a code-generating AI model similar to GitHub's Copilot.

Learn one of the ways in which AI has elevated my design work.

Weaver is a useful Obsidian plugin that integrates ChatGPT/GPT-3 into your note-taking workflow. This plugin makes it easy to access AI-generated suggestions and insights within Obsidian, helping y...

A little bit of magic, but mostly just practice

News Minimalist filters out the noise so you don't have to. We analyze the top 1,000 news daily, bringing you only the essentials in our 2-minute newsletter.

‎Poe lets you ask questions, get instant answers, and have back-and-forth conversations with AI. Gives access to GPT-4, gpt-3.5-turbo, Claude from Anthropic, and a variety of other bots. Poe includes both free and subscription bots. Payments for subscriptions will be charged to your Apple ID at conf…

Colab LaMini-LM Neo 1.3B: https://colab.research.google.com/drive/1JkbeqGDp_UIi12lv0CltJhFyzIqvY_1N?usp=sharing Colab LaMini-LM GPT1.5B: https://colab.research.google.com/drive/1wAfYXYECNIeub0hS05c7BRTY2a26qd53?usp=sharing Colab LaMini-Flan-T5-783M: https://colab.research.google.com/drive/1fJrwbqYFQa1wJ3xJelZ9gjTxcDnCqumb?usp=sharing Github: https://github.com/mbzuai-nlp/LaMini-LM Dataset: https://huggingface.co/datasets/MBZUAI/LaMini-instruction/ Paper: https://arxiv.org/abs/2304.14402 In this video I go through the paper LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions and examine how they created the dataset and models for this paper and project. 00:00 Intro 00:45 Key Idea 01:23 Diagram 01:45 Dataset 02:10 Hugging Face Dataset 02:27 Trained on a lot of Models 03:05 Paper 04:36 Prompts on ChatGPT 09:37 Code Time

Multiversal tree writing interface for human-AI collaboration - socketteer/loom: Multiversal tree writing interface for human-AI collaboration

Omni is a contextual real-time information retrieval system to augment intellectual work with the most relevant information across all websites, all books, all scientific literature, and all personal writing.

LangChain has become a tremendously popular toolkit for building a wide range of LLM-powered applications, including chat, Q&A and document search. In this blogpost I re-implement some of the novel LangChain functionality as a learning exercise, looking at the low-level prompts it uses to create these higher level capabilities.

Large Language Models (LLMs) have a data freshness problem. Even some of the most powerful models, like ChatGPT's gpt-3.5-turbo and GPT-4, have no idea about...

A Bulletproof Way to Generate Structured JSON from Language Models - GitHub - 1rgs/jsonformer: A Bulletproof Way to Generate Structured JSON from Language Models

Note: This post assumes some familiarity with LangChain and is moderately technical. 💡 TL;DR: We’ve introduced a new abstraction and a new document Retriever to facilitate the post-processing of retrieved documents. Specifically, the new abstraction makes it easy to take a set of retrieved documents and extract from them

OpenAI, creators of ChatGPT, join the show! In November 2022, ChatGPT upended the tech (and larger) world with a chatbot that passes not only the Turing test, but the bar exam. In this episode, we talk with Dave Willner and Todor Markov, integrity professionals at OpenAI, on how they make large lan

Leaked Internal Google Document Claims Open Source AI Will Outcompete Google and OpenAI

Midjourney released version 5.1 of their image generation model on Tuesday. Here’s their announcement on Twitter—if you have a Discord account there’s a more detailed Discord announcement here. They claim …

Theoretical fund of 38 stocks do better than 10 most popular funds on Interactive Investor, finds finder.com

Online learning nonprofit Khan Academy's new tool is trained to act as a tutor and teacher’s assistant.

Before a White House meeting with Google and Microsoft.

The Biden Administration vows to invest $140 million on seven new AI R&D centers and browbeat Big Tech into behaving..

Jeremy Howard makes a very convincing argument for why the new programming language Mojo is a big deal. Mojo is a superset of Python designed by a team lead by …

Yesterday Chris Lattner announced a new programming language called Mojo, which builds on top of Python and is designed specifically for AI applications. They claim it’s up to 35000 times faster than Python. So let’s take a quick first look at it. Website: https://www.modular.com/mojo Docs: https://docs.modular.com/mojo/ Keynote: https://youtu.be/-3Kf2ZZU-dg Get my Free NumPy Handbook: https://www.python-engineer.com/numpybook ✅ Write cleaner code with Sourcery, instant refactoring suggestions in VS Code & PyCharm: https://sourcery.ai/?utm_source=youtube&utm_campaign=pythonengineer * ⭐ Join Our Discord : https://discord.gg/FHMg9tKFSN 📓 ML Notebooks available on Patreon: https://www.patreon.com/patrickloeber If you enjoyed this video, please subscribe to the channel: ▶️ : https://www.youtube.com/channel/UCbXgNpp0jedKWcQiULLbDTA?sub_confirmation=1 ~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~ 🖥️ Website: https://www.python-engineer.com 🐦 Twitter - https://twitter.com/patloeber ✉️ Newsletter - https://www.python-engineer.com/newsletter 📸 Instagram - https://www.instagram.com/patloeber 🦾 Discord: https://discord.gg/FHMg9tKFSN ▶️ Subscribe: https://www.youtube.com/channel/UCbXgNpp0jedKWcQiULLbDTA?sub_confirmation=1 ~~~~~~~~~~~~~~ SUPPORT ME ~~~~~~~~~~~~~~ 🅿 Patreon - https://www.patreon.com/patrickloeber #Python Timeline: 00:00 - Intro & motivation 01:23 - Features 04:48 - How to try Mojo ---------------------------------------------------------------------------------------------------------- * This is an affiliate link. By clicking on it you will not have any additional costs, instead you will support me and my project. Thank you so much for the support! 🙏