Finding some old floppy disks I wondered how I could read them. Assuming that I have a floppy reader, how could I then open some of the old file formats? A quick search led me first to the “Mini vMac” site but this option only emulates very old Macs and has the complication that one… Read More »
Generative pre-trained models are becoming more common by the day, and such methods have now been applied to single cell sequencing, and multi-omits in general. Two main players are “scBERT” and “scGPT”: scGPT: Towards Building a Foundation Model for Single-Cell Multi-omics Using Generative AIHaotian Cui, Chloe Wang, Hassaan Maan, Bo Wang – Nature Methods doi: 10.1038/s41592-024-02201-0 CODE: https://github.com/bowang-lab/scGPT scBERT as a large-scale pretrained deep language… Read More »
Source: https://arstechnica.com/information-technology/2024/03/once-too-scary-to-release-gpt-2-gets-squeezed-into-an-excel-spreadsheet/ This Blog: Once “too scary” to release, GPT-2 gets squeezed into an Excel spreadsheet OpenAI’s GPT-2 running locally in Microsoft Excel teaches the basics of how LLMs work. by Benj Edwards – 3/15/2024, 3:56 PM Summary by Copilot: (Edited) Ishan Anand, a software developer, has created a Microsoft Excel spreadsheet that runs “GPT-2”… Read More »
These 2 videos are quite cool (in spite of the vocal fry speech) and teach a lot about quantum computing and q-bits in ways that make sense to a non-physicist… Video 1: 25:38 min – I made a (useless) quantum computer at home Video 2: 33:15 min – What can my homemade quantum computer do?… Read More »
This is available as a plug-in for Chrome or Safari. It is free for videos that are less than 30 min. The plug-in is available at eightify.app Eightify is a cutting-edge program made to assist users in condensing the main points of lengthy YouTube films. It’s now simpler to swiftly create summaries of YouTube videos… Read More »
This is a short version of Do yourself a favor: learn Markdown – Episode 7: BibTeX for online articles Summary: Generate BibTeX from URL for web pages, blogs, articles online, etc. In a previous article (Sgro (2022)) I presented how to add bibliographical information within an Rmarkdown document (Allaire et al. (2023)) with the BibTex format in… Read More »
This video from November 22, 2023 provides a general introduction to Large Language Models (LLMs) suitable for general understanding. The video continues to examples, possible upcoming paradigms such as the view that LLMs have similarities with operating systems. The final part details potentials threats, including jailbreak examples. What’s wrong with LLMs and what we should… Read More »
Yesterday, December 06, 2023, Alphabet, the parent company of Google Mind AI, has released Gemini, in fact 3 different versions (Ultra, Pro, and Nano.) (See also video below.) The previous Google AI “Bard” has been updated to become Gemini Pro as of December 6th as it will reply if you ask it/him/her/them: If you’re using… Read More »
AI is at the forefront of Society changes. We are at the dawn of a new world. Let’s hope that it will NOT be a “Brave New World“. Today I discovered (through a LinkedIn post by the group “Generative AI” which has 1.3M followers.) This brand new AI is called “youai.ai” with mostly free “mini-AI”… Read More »
As described in the previous blog titled AI chat models at the command line I have implemented the procedure that was used for the 7B LLMA to that of the 65B model. Still on the same Mac running Mac OS Ventura, on an i5 6-cores Intel chip, 16Gb RAM. The files and models are kept… Read More »