AI Everyday

AI Everyday #21 - Phind, a CodeLlama fine-tune, beating GPT4 at HumanEval

September 13, 2023 Matthew Wallace

AI Everyday

Sep 13, 2023

Matthew Wallace

Matt discusses his results from testing Phind-CodeLlama-34B-v2, which beat the GPT-4 zero-shot HumanEval test by a good margin.

Listen on

Apple Podcasts Spotify Amazon Music Podcast Index Overcast iHeartRadio +

Share Episode

Matt discusses his results from testing Phind-CodeLlama-34B-v2, which beat the GPT-4 zero-shot HumanEval test by a good margin.