There's a new LLM bird in town! Meet Eagle-7B, the latest model based on the RWKV-v4 architecture that outperforms SOTA 7B LLM models like Mistral and Falcon. Unlike transformer-based LLM...
Read more → The RAG vs Fine-Tuning debate is always interesting, so when this comprehensive evaluation study was released, I had to read it. A comprehensive evaluation of LLMs including base models, with...
Read more → The paper "Chain-Of-Table" proposes expanding upon the existing Chain-Of-Thought (CoT) reasoning, particularly for complex table-based data with Large Language Models (LLMs). The authors propose adding intermediate tables iteratively into the...
Read more → Recently, arXiv.org added an experimental feature to render papers in HTML format. I did not think much of it until I realized you could now send these to Kindle like...
Read more → Llamafile is the new simplest solution to run an LLM locally on your computer and prototype quickly. It works in just 3 steps: 1. Download a Llamafile from a repository...
Read more →