301
Run Llama 2 uncensored locally
This post will give some example comparisons running Llama 2 uncensored model versus its censored model.
New
The latest blog posts to take off on Hacker News. 789 posts.
302
Open-sourcing AudioCraft: Generative AI for audio
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.
303
Edge detection doesn’t explain line drawing
Reasons to be skeptical of the conventional wisdom about line drawing perception
304
Patterns for building LLM-based systems and products
Evals, RAG, fine-tuning, caching, guardrails, defensive UX, and collecting user feedback.
305
Nvidia H100 GPUs: Supply and Demand
This post is an exploration of the supply and demand of GPUs, particularly Nvidia H100s.
306
Gzip beats BERT? Part 2: dataset issues, improved speed, and results
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 .
307
So you want to build your own open source chatbot
A small team within Mozilla’s innovation group recently undertook a hackathon to build a trustworthy internal chatbot prototype.
308
LeMUR: LLMs for Audio and Speech
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.
309
310
LLMs Unleashed: The Power of Fine-Tuning
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…
311
LLaMA2 Chat 70B outperformed ChatGPT
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…
312
OverflowAI
Let’s highlight the new features and products we announced today from the stage of WeAreDevelopers.
313
How to scale LLMs better with an alternative to transformers
Monarch Mixer: Revisiting BERT, Without Attention or MLPs
314
Which GPU(s) to Get for Deep Learning
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.
315
Guide to running Llama 2 locally
How to run Llama 2 on Mac, Linux, Windows, and your phone.
316
We're not Platonists, we've just learned the bitter lesson
Machine Alignment Monday, 7/24/23
317
What we know about LLMs
~Will Thompson's personal website~
318
From Python to Elixir Machine Learning
Moving on from Python Machine Learning might seem impossible. Let me break down why and how you can do it.
319
A simple guide to fine-tuning Llama 2
Brev.Dev Instances Console
320
Attention Is Off By One
Let’s fix these pesky Transformer outliers using Softmax One and QuietAttention.
321
Teach your LLM to answer with facts, not fiction
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
322
FreeWilly 1 and 2, two new open-access LLMs
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.
323
324
Custom instructions for ChatGPT
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.
325
TypeChat
July 20, 2023 by Anders Hejlsberg, Steve Lucco, Daniel Rosenwasser, Pierce Boggan, Umesh Madan, Mike Hopcroft, and Gayathri Chandrasekaran
326
A framework to securely use LLMs in companies – Part 1: Overview of Risks
Part 1 of a multi-part series on using LLMs securely within your organisation. This post provides a framework to categorize risks based on different use cases and deployment type.
327
Use pytorch2+cu118 with ADA hardware for 50%+ speedup
GPUX is a distributed supercomputer.
328
SHOW-1 and Showrunner Agents in Multi-Agent Simulations
South Park AI is an example of how to generate high-quality episodic content through the use of showrunner agents in the simulation. #AI #simulation #multi-agent
329
330
Accessing Llama 2 from the command-line with the LLM-replicate plugin
The big news today is Llama 2, the new openly licensed Large Language Model from Meta AI. It’s a really big deal: Llama 2 is available for free for research …