Best of LLM — April 2024
- 1
- 2
freeCodeCamp·2y
Mastering RAG from Scratch
Learn how to implement Retrieval-Augmented Generation (RAG) from scratch with an in-depth course on the freeCodeCamp.org YouTube channel. RAG combines retrieval systems with advanced natural language generation and is valuable in chatbot development and other fields.
- 3
Machine Learning News·2y
Meet AnythingLLM: An Open-Source, All-in-One AI Desktop App for Local LLMs + RAG
AnythingLLM is an open-source, all-in-one AI desktop app for local LLMs and RAG. It empowers users to deploy private ChatGPT instances capable of intelligent conversations based on the content of provided documents. AnythingLLM offers multi-user support, custom embeddable chat widget, multiple document type support, efficient document management, conversation and query modes, in-chat citations, cloud deployment readiness, support for various LLMs, and a developer-friendly API.
- 4
How to Run Open Source LLMs Locally Using Ollama
Learn how to download and use Ollama, a powerful tool for interacting with open-source large language models (LLMs) on your local machine. Explore the LLaMA 2 text-based model and the LLaVA multimodal model. Download Ollama and unleash the potential of open-source LLMs!
- 5
- 6
Hacker News·2y
LLaMA Now Goes Faster on CPUs
LLaMa Now Goes Faster on CPUs: New matrix multiplication kernels have been developed for llamafile, resulting in improved performance for prompt evaluation time. The improvements are most noticeable for certain weights and specific CPU types such as ARMv8.2+, Intel Alderlake, and AVX512. The new kernels outperform MKL for matrices that fit in L2 cache and offer potential for faster evaluation speed.
- 7
- 8
What can LLMs never do?
LLMs face limitations in playing certain games like Conway's Game of Life and struggle with reasoning tasks that require longer series of steps. They also exhibit the Reversal Curse, where their training data does not enable them to answer reverse-structured questions. However, with proper prompting and intermediate access to memory and computation, they can be trained to predict cellular automata to some extent.
- 9
- 10
- 11
Community Picks·2y
Large language models, explained with a minimum of math and jargon
This post explains how large language models work, including how they represent words using vectors, how they predict the next word, and how they are trained. It also discusses the surprising performance of GPT-3 on tasks requiring high-level reasoning and its potential to understand meanings of words.
- 12
Data Science Central·2y
2 addressing the limitations of RAG
The post explores the limitations of RAG and introduces the idea of a GRAPHRAG to overcome these limitations by combining a knowledge graph with RAG. Graph RAG enriches the standard LLM approach with structured information from a knowledge graph.
- 13
Irrational Exuberance·2y
My advice for how to use LLMs in your product.
Advice on using LLMs in products, mental models, revamping workflows, retrieval augmented generation (RAG), rate of innovation, human-in-the-loop (HITL), hallucinations and legal liability, zero to one versus one to N, copyright law, data processing agreements, and provider availability.
- 14
AI in Plain English·2y
LLaMA3: A New Era in Large Language Models
LLaMA3 is a powerful AI tool that represents a significant step forward in large language models. It aims to democratize access to state-of-the-art language models and has the potential to contribute to the development of Artificial General Intelligence (AGI).
- 15
- 16
- 17
