The latest blog posts to take off on Hacker News. 6,334 posts.
It’s well-known at this point that GPT-4/GPT-3.5-turbo is non-deterministic, even at temperature=0.0. This is an odd behavior if you’re used to dense decoder-only models, where temp=0 should imply greedy sampling which should imply full determinism, because the logits for the next token should be a pure function of…
The AI Code Copilot has been replaced by the more powerful AI Chat feature.
I gave a talk on Sunday at North Bay Python where I attempted to summarize the last few years of development in the space of LLMs—Large Language Models, the technology …
IBM & open-source AI platform Hugging Face today announced that IBM's watsonx.ai geospatial foundation model – built from NASA's satellite data – will now be openly available on Hugging Face.
Both Butterscotch Varifocal and Flamera are very much in the research stage, and the technologies they’re investigating may never make their way into a consumer-facing product. And, as we hope you’ll come to see, that’s very much the point.
An operational guide on finetuning Llama 2, ready for commercial use.
This post will give some example comparisons running Llama 2 uncensored model versus its censored model.
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.
Reasons to be skeptical of the conventional wisdom about line drawing perception
Evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback.
This post is an exploration of the supply and demand of GPUs, particularly Nvidia H100s.
Summary : Update to my last post analyzing the gzip+knn paper. Some of the datasets have heavily contaminated train/test tests. I show some ways to significantly speed-up the gzip method. I present more results of my "fair" reimplementation .
A small team within Mozilla’s innovation group recently undertook a hackathon to build a trustworthy internal chatbot prototype.
Introducing LeMUR, our new framework for applying powerful LLMs to transcribed speech With a single line of code, LeMUR can quickly process audio transcripts for up to 10 hours worth of audio content, which effectively translates into ~150k tokens, for tasks like summarization and question answer.
Disclaimer: This article mentions https://terra-cotta.ai/, an LLM experimentation platform I am building Introduction ChatGPT, Bard, and other large language models (LLMs) are very useful for a wide variety of tasks from writing code to answering complex questions to aiding with education. However, these models are…
AlpacaEval an LLM-based automatic evaluation that is fast, cheap, and reliable. It is based on the AlpacaFarm evaluation set, which tests the ability of models to follow general user instructions. These responses are then compared to reference responses (Davinci003 for AlpacaEval, GPT-4 Preview for AlpacaEval 2.0) by…
Let’s highlight the new features and products we announced today from the stage of WeAreDevelopers.
Monarch Mixer: Revisiting BERT, Without Attention or MLPs
Here, I provide an in-depth analysis of GPUs for deep learning/machine learning and explain what is the best GPU for your use-case and budget.
How to run Llama 2 on Mac, Linux, Windows, and your phone.
Machine Alignment Monday, 7/24/23
~Will Thompson's personal website~
Moving on from Python Machine Learning might seem impossible. Let me break down why and how you can do it.
Brev.Dev Instances Console
Let’s fix these pesky Transformer outliers using Softmax One and QuietAttention.
Learn how to train LLM for accurate answers with VectorSQL which allows you to execute finely-grained vector searches to target and retrieve the required information
Stability AI and its CarperAI lab are proud to announce FreeWilly1 and its successor FreeWilly2, two powerful new, open access, Large Language Models (LLMs). Both models demonstrate exceptional reasoning ability across varied benchmarks.
We’re rolling out custom instructions to give you more control over how ChatGPT responds. Set your preferences, and ChatGPT will keep them in mind for all future conversations.
