emasters

[emasters]

Working with David Colarusso's LIT Prompts Browser Extension

Today’s adventures in generative AI included using David Colarusso’s LIT Prompts Chrome extension connected to the OpenAI gpt-4o-mini API on Chapter 4 of Alice Ristroph’s Criminal Law: An Integrated Approach. I first requested a short 150 word summary of the chapter which is one of the default prompts in this extension. Then using info from that summary I asked questions about Winship.  The…

[emasters]

Using generative AI to create a contracts quiz

AI for Everybody: Using generative AI to create a contracts quiz

Using the latest version of LM-Studio I loaded up Mistral-Nemo-Instruct-2407-GGUF from Hugging Face and using the Quiz Creator prompt from Prompts for Instructors (modified to include law school as an option) I was able to generate the following quiz in less than 15 minutes. Note: I did need to ask it to generate model answers for the open ended questions but I think the prompt can be further…

[emasters]

Drupal 11.0 will require PHP 8.3 and MySQL 8.0

Drupal 11 development has reached a point where the system requirements are being raised in the development branch. To prepare core developers for this and to inform the community at large, we are announcing the following requirements for Drupal 11. … Drupal 11 will require PHP 8.3 and older versions of PHP are not supported. … The minimum database requirements for backends supported by Drupal 11…

[emasters]

StarCoder2 - open source code completion models

StarCoder2 is a family of code generation models (3B, 7B, and 15B), trained on 600+ programming languages from The Stack v2 and some natural language text such as Wikipedia, Arxiv, and GitHub issues. The models use Grouped Query Attention, a context window of 16,384 tokens, with sliding window attention of 4,096 tokens. The 3B & 7B models were trained on 3+ trillion tokens, while the 15B was…

[emasters]

Drupal and CKEditor: a history of advanced content editing | CKEditor

Explore the evolution of content editing in Drupal with CKEditor 5, uncover key features, real-world applications, and future plans. Source: Drupal and CKEditor: a history of advanced content editing | CKEditor

[emasters]

Drupal 11 is now open for development, Drupal 10.3.x is branched

Starting today, the Drupal 11.x branch is used for building the next major Drupal version, Drupal 11. This means that major version specific changes can now happen on the Drupal 11.x branch. This includes dependency and requirements updates and removal of deprecated API and extensions. Details are available in the allowed changes during Drupal core release cycle document. Drupal 11 is planned to…

[emasters]

Drupal core committers look to remove support for Windows in production in Drupal 11

Drupal added support for IIS in 2010 and we have supported that and WAMP (Running Apache and PHP on Windows). Unfortunately, we have never been able to provide automated testing for these environments. And since 2010, the use of Microsoft products for hosting websites has declined. Because of this, the Drupal core committers propose drop support for Windows when used on production web sites in…

[emasters]

PC Magazine :: Don't Run Out of Space: How to Move PC Games to a Different Hard Drive

If your hard drive is running out of space, you can move your collection of PC games to a different drive. Here’s how to set up the move from your game client of choice. Source: Don’t Run Out of Space: How to Move PC Games to a Different Hard Drive

[emasters]

💥 Training Neural Nets on Larger Batches: Practical Tips for 1-GPU, Multi-GPU & Distributed setups | by Thomas Wolf | HuggingFace | Medium

Training neural networks with larger batches in PyTorch: gradient accumulation, gradient checkpointing, multi-GPUs and distributed setups… Source: 💥 Training Neural Nets on Larger Batches: Practical Tips for 1-GPU, Multi-GPU & Distributed setups | by Thomas Wolf | HuggingFace | Medium

[emasters]

Productionizing and scaling Python ML workloads simply | Ray

Scale your compute-intensive Python workloads. From reinforcement learning to large-scale model serving, Ray makes the power of distributed compute easy and accessible to every engineer. Source: Productionizing and scaling Python ML workloads simply | Ray

[emasters]

Building a Multi-User Chatbot with Langchain and Pinecone in Next.JS

In this example, we’ll imagine that our chatbot needs to answer questions about the content of a website. To do that, we’ll need a way to store and access that information when the chatbot generates its response. Source: Building a Multi-User Chatbot with Langchain and Pinecone in Next.JS

[emasters]

Mountpoint for Amazon S3 – Generally Available and Ready for Production Workloads | AWS News Blog

Mountpoint for Amazon S3 is an open source file client that makes it easy for your file-aware Linux applications to connect directly to Amazon Simple Storage Service (Amazon S3) buckets. Announced earlier this year as an alpha release, it is now generally available and ready for production use on your large-scale read-heavy applications: data lakes, machine learning training, image rendering,…

[emasters]

AudioCraft: A simple one-stop shop for audio modeling

AudioCraft is a simple framework that generates high-quality, realistic audio and music from text-based user inputs after training on raw audio signals as opposed to MIDI or piano rolls. Source: AudioCraft: A simple one-stop shop for audio modeling

[emasters]

Meet Academic Standards With These Essential WordPress Plugins For Scholarly Content

Enhance your academic content’s credibility and make navigation of your articles easier on WordPress with these essential plugins. Source: Meet Academic Standards With These Essential WordPress Plugins For Scholarly Content

[emasters]

Notes on better search 8/18/2023

Goal: better, more focused search for http://www.cali.org. In general the plan is to scrape the site to a vector database, enable embeddings of the vector db in Llama 2, provide API endpoints to search/find things. Hints and pointers. Llama2-webui – Run any Llama 2 locally with gradio UI on GPU or CPU from anywhere FastAPI – web framework for building APIs with Python 3.7+ based on standard…

[emasters]

Demystifying Text Data with the unstructured Python Library | Saeed Esmaili

In the world of data, textual data stands out as being particularly complex. It doesn’t fall into neat rows and columns like numerical data does. As a side project, I’m in the process of developing my own personal AI assistant. The objective is to use the data within my notes and documents to answer my questions. The important benefit is all data processing will occure locally on my computer,…

[emasters]

AI Reading List 7/6/2023

What I’m reading today. Researchers from Peking University Introduce ChatLaw: An Open-Source Legal Large Language Model with Integrated External Knowledge Bases — This includes links to the article and Github repo Why Embeddings Usually Outperform TF-IDF: Exploring the Power of NLP Fine-tune an LLM on your personal data: create a “The Lord of the Rings” storyteller Open Assistant — In the same…