Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Teknium, Ryan, Jin, Roger, Suphavadeeprasit, Jai, Mahan, Dakota, Quesnelle, Jeffrey, Li, Joe, Guang, Chen, Sands, Shannon, Malhotra, Karan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.18255
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911132902490112
author Teknium, Ryan
Jin, Roger
Suphavadeeprasit, Jai
Mahan, Dakota
Quesnelle, Jeffrey
Li, Joe
Guang, Chen
Sands, Shannon
Malhotra, Karan
author_facet Teknium, Ryan
Jin, Roger
Suphavadeeprasit, Jai
Mahan, Dakota
Quesnelle, Jeffrey
Li, Joe
Guang, Chen
Sands, Shannon
Malhotra, Karan
contents We present Hermes 4, a family of hybrid reasoning models that combine structured, multi-turn reasoning with broad instruction-following ability. We describe the challenges encountered during data curation, synthesis, training, and evaluation, and outline the solutions employed to address these challenges at scale. We comprehensively evaluate across mathematical reasoning, coding, knowledge, comprehension, and alignment benchmarks, and we report both quantitative performance and qualitative behavioral analysis. To support open research, all model weights are published publicly at https://huggingface.co/collections/NousResearch/hermes-4-collection-68a731bfd452e20816725728
format Preprint
id arxiv_https___arxiv_org_abs_2508_18255
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hermes 4 Technical Report
Teknium, Ryan
Jin, Roger
Suphavadeeprasit, Jai
Mahan, Dakota
Quesnelle, Jeffrey
Li, Joe
Guang, Chen
Sands, Shannon
Malhotra, Karan
Artificial Intelligence
We present Hermes 4, a family of hybrid reasoning models that combine structured, multi-turn reasoning with broad instruction-following ability. We describe the challenges encountered during data curation, synthesis, training, and evaluation, and outline the solutions employed to address these challenges at scale. We comprehensively evaluate across mathematical reasoning, coding, knowledge, comprehension, and alignment benchmarks, and we report both quantitative performance and qualitative behavioral analysis. To support open research, all model weights are published publicly at https://huggingface.co/collections/NousResearch/hermes-4-collection-68a731bfd452e20816725728
title Hermes 4 Technical Report
topic Artificial Intelligence
url https://arxiv.org/abs/2508.18255