NousResearch Hugging Face Profile: Hermes Models and Research

LinkNousResearchResource

NousResearch's Hugging Face organisation profile hosts open-source language models from the Hermes 4 family, evaluation datasets from their technical report, and research papers.

Key points

  1. NousResearch focuses on advancing natural language processing in collaboration with the open-source community.
  2. The Hermes 4 collection includes weights across multiple sizes: Hermes-4-14B, Hermes-4.3-36B, Hermes-4-70B, and Hermes-4-405B-FP8.
  3. Evaluation datasets from the Hermes-4 Technical Report cover both reasoning and non-reasoning benchmarks.
  4. Research publications include work on byte-level simulation for subword tokenisation and targeted neuron modulation.
  5. The profile features an interactive Space showcasing CNA refusal ablation with Qwen2.5-14B-Instruct.

Why it matters

NousResearch provides the open-source ecosystem with versatile, fine-tuned instruction models and publishes accompanying benchmark data for independent verification.

Analysis

By offering models scaling from 14B to 405B FP8 alongside raw evaluation files, NousResearch supports both resource-constrained self-hosting and high-end experimentation. Their public assets reflect a dual commitment to model weights and empirical research transparency.

Found in

Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.

Similar in content, found by the AI search.

  • Link:Open LLM Leaderboard Team

    Hugging Face Open LLM Leaderboard

    The organisation maintaining the Open LLM Leaderboard on Hugging Face provides datasets and benchmarks to track, rank, and evaluate open LLMs and chatbots.

    AI & LLMs· Resource

  • Link:Nous Research

    Hermes Agent: Open-Source AI Agent by Nous Research

    Nous Research has released Hermes Agent v0.21.0 under the MIT licence. The tool serves as an extensible AI agent available across multiple operating systems and messaging channels, featuring persistent memory and isolated execution sandboxes.

    AI & LLMs· Tool

  • Repository:NousResearch/hermes-agent

    Hermes Agent: Self-Improving Open Source AI Agent by Nous Research

    Hermes Agent is a cross-platform, self-improving AI agent designed with an autonomous learning loop, cross-session memory, and integration into multiple messaging platforms and terminal interfaces.

    240.8kstarsPython

    AI & LLMs· Tool

  • Link:Nous Research

    Hermes Bots Guide: Practitioner's Guide to Multi-Agent Systems by Nous Research

    Nous Research has published a guide covering Bot Mode in Hermes Agent. The feature enables users to run isolated agent profiles as named, persistent bots that execute recurring routines, expand their own skills, and interact across more than 20 messaging platforms.

    AI & LLMs· Resource

Let's talk about your project

Locations

  • Mattersburg
    Johann Nepomuk Bergerstraße 7/2/14
    7210 Mattersburg, Austria
  • Vienna
    Ungargasse 64-66/3/404
    1030 Wien, Austria

Parts of this content were created with the assistance of AI.