vault backup: 2024-03-13 - 2 files

Affected files: Monthly Notes/Mar 2024 notes.md README.md
swyxio · Mar 14, 2024 · 2488adf · 2488adf
1 parent 85c9a3a
commit 2488adf
Show file tree

Hide file tree

Showing 2 changed files with 2 additions and 0 deletions.
diff --git a/Monthly Notes/Mar 2024 notes.md b/Monthly Notes/Mar 2024 notes.md
@@ -54,6 +54,7 @@
 - [Moondream2](https://x.com/vikhyatk/status/1764793494311444599?s=20) - a small, open-source, vision language model designed to run efficiently on edge devices. Clocking in at 1.8B parameters, moondream requires less than 5GB of memory to run in 16 bit precision. This version was initialized using Phi-1.5 and SigLIP, and trained primarily on synthetic data generated by Mixtral. Code and weights are released under the Apache 2.0 license, which permits commercial use.
 - OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on: https://github.com/levihsu/OOTDiffusion
 - [Yi: Open Foundation Models by 01.AI](https://news.ycombinator.com/item?id=39659781)  paper covering Yi--34B and variants
+- [LaVague: Open-source Large Action Model to automate Selenium browsing](https://github.com/lavague-ai/LaVague) ([HN](https://news.ycombinator.com/item?id=39698546))
 
 ## Open source tooling
 

diff --git a/README.md b/README.md
@@ -172,6 +172,7 @@ The more advanced GPT3 reads have been split out to https://github.com/sw-yx/ai-
 	    -   Data Poisoning & Backdoor Attacks
 	- [Evan Morikawa guide to LLM math](https://newsletter.pragmaticengineer.com/p/scaling-chatgpt) especially the 5 scaling challenges piece
   -  [A Hacker's Guide to Language Models](https://twitter.com/jeremyphoward/status/1705883362991472984?s=20)  ([youtube](https://youtu.be/jkrNMKz9pWU?si=BNz-v6VmdbX7QDtr)) Jeremy Howard's 90min complete overview of LLM learnings - starting at the basics: the 3-step pre-training / fine-tuning / classifier ULMFiT approach used in all modern LLMs.
+  - https://spreadsheets-are-all-you-need.ai
   - ["Catching up on the weird world of LLMs"](https://simonwillison.net/2023/Aug/3/weird-world-of-llms/) - Simon Willison's 40min overview + [Open Questions for AI Engineers](https://www.youtube.com/watch?v=AjLVoAu-u-Q)
   - [LLMs overview from Flyte](https://flyte.org/blog/getting-started-with-large-language-models-key-things-to-know#what-are-llms)
   - [Patterns for building LLM-based systems and products](https://eugeneyan.com/writing/llm-patterns/) - great recap