Enregistré dans:
Détails bibliographiques
Auteurs principaux: Teknium, Ryan, Quesnelle, Jeffrey, Guang, Chen
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2408.11857
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914920506851328
author Teknium, Ryan
Quesnelle, Jeffrey
Guang, Chen
author_facet Teknium, Ryan
Quesnelle, Jeffrey
Guang, Chen
contents Instruct (or "chat") tuned models have become the primary way in which most people interact with large language models. As opposed to "base" or "foundation" models, instruct-tuned models are optimized to respond to imperative statements. We present Hermes 3, a neutrally-aligned generalist instruct and tool use model with strong reasoning and creative abilities. Its largest version, Hermes 3 405B, achieves state of the art performance among open weight models on several public benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2408_11857
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hermes 3 Technical Report
Teknium, Ryan
Quesnelle, Jeffrey
Guang, Chen
Computation and Language
Instruct (or "chat") tuned models have become the primary way in which most people interact with large language models. As opposed to "base" or "foundation" models, instruct-tuned models are optimized to respond to imperative statements. We present Hermes 3, a neutrally-aligned generalist instruct and tool use model with strong reasoning and creative abilities. Its largest version, Hermes 3 405B, achieves state of the art performance among open weight models on several public benchmarks.
title Hermes 3 Technical Report
topic Computation and Language
url https://arxiv.org/abs/2408.11857