aifaq.wtf

"How do you know about all this AI stuff?"
I just read tweets, buddy.

#performance

Page 1 of 1

Improving Search Ranking with Few-Shot Prompting of LLMs

blog.vespa.ai

Distilling the knowledge and power of generative Large Language Models (LLMs) with billions of parameters to ranking models with a few million parameters.

Improving Search Ranking with Few-Shot Prompting of LLMs

February 16, 2024

#fine-tuning #shortcuts #local models #models #performance #evaluation #link

This is good in combination with Hugging Face's Synthetic data: save money, time and carbon with open source.

Source: https://blog.vespa.ai/improving-text-ranking-with-few-shot-prompting/

Synthetic data: save money, time and carbon with open source

huggingface.co

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

Synthetic data: save money, time and carbon with open source

February 16, 2024

#synthetic data #hugging face #fine-tuning #performance #zero-shot classification #few-shot classification #classification #evaluation #link

This post does a fantastic job breaking down how you use an expert labeler (teacher LLM) to annotate your data, then use it to fine-tune a student LLM. It's as good or better than crowd workers!

In this case they use Mixtral to prep data for RoBERTa-base, then get equal performance in the end. So much faster! So much cheaper!

Source: https://huggingface.co/blog/synthetic-data-save-costs