# DFM Mimir v1：仅用合规后训练数据，1B 参数开源 HRM 模型实现前沿性能

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-13 08:00
- AIHOT 分数：61
- AIHOT 链接：https://aihot.virxact.com/items/cmsx8xsyg05qlrommwr7vtsbs
- 原文链接：https://arxiv.org/abs/2608.13517

## AI 摘要

DFM 发布 Mimir v1，一个基于 Hierarchical Reasoning Model（HRM）架构的 10 亿参数语言模型，从头训练并仅使用合规后训练数据，在英语上表现极具竞争力，并在丹麦语上创下新 SOTA。

## 正文

Current large language model development relies on massive, often non-permissible datasets, creating a high barrier for researchers committed to open-source and ethically sourced data. We introduce Mimir v1, a 1-billion-parameter language model based on the Hierarchical Reasoning Model (HRM) architecture, that is trained from scratch and delivers highly competitive performance for English and sets a new state of the art for Danish using only permissible post-training data. Trained on a mixture of 161 datasets, Mimir v1 outperforms the original HRM-Text 1B and competes with larger frontier models like Qwen 3.5 4B and Gemma 4 E2B, tested across 20 benchmarks for English, Math & Code and Danish. The model is available on the Hugging Face Hub: https://huggingface.co/danish-foundation-models/DFM-Mimir