AI Everyday #21 - Phind, a CodeLlama fine-tune, beating GPT4 at HumanEval Podcast Por  arte de portada

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

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

Escúchala gratis

Ver detalles del espectáculo

Acerca de esta escucha

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

Todavía no hay opiniones