Why Emacs is the best platform for LLMs

• ekg

  9 192 9.2 Emacs Lisp

  The emacs knowledge graph, app for notes and structured data. (by ahyatt)

This is an exciting time. In the world of text, emacs is hard to beat! Thanks to those already working on their own packages, which I hope continue to evolve. Personally, I'd like for my ekg package to act as a prompt repository, and am exploring ways to make this useful.

• llama

  184 53,053 8.1 Python

  Inference code for Llama models

  

Yes, you can run Meta's llama (https://github.com/facebookresearch/llama). However, that's running someone else's model. Training a model is a big endeavor, requiring 10s of millions of dollars of compute time, months of processing, and a lot of expertise. And I think it's dubious that we anyone to just be able to create these (see my post above where I link to GPT4's paper that has some pretty disturbing questions that a trained LLM can absolutely answer, but most people, including me, wouldn't want it to).

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project