# Salamandra Technical Report

arXiv: https://arxiv.org/abs/2502.08489 · HTML: https://mlsanity.com/paper/2502.08489/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2025.

## Built on by (most cited first, 10 of 10)

- [Speech-to-Text Translation with Phoneme-Augmented CoT: Enhancing Cross-Lingual Transfer in Low-Resource Scenarios](https://mlsanity.com/paper/2505.24691/) (2025)
- [ALBA: A European Portuguese Benchmark for Evaluating Language and Linguistic Dimensions in Generative LLMs](https://mlsanity.com/paper/2603.26516/) (2026)
- [TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation](https://mlsanity.com/paper/2603.08182/) (2026)
- [Listening or Reading? Evaluating Speech Awareness in Chain-of-Thought Speech-to-Text Translation](https://mlsanity.com/paper/2510.03115/) (2025)
- [XDoGE: Multilingual Data Reweighting to Enhance Language Inclusivity in LLMs](https://mlsanity.com/paper/2512.10545/) (2025)
- [A Sovereign, Open-Source Foundation Model for German and English](https://mlsanity.com/paper/2607.09424/) (2026)
- [Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos](https://mlsanity.com/paper/2602.15757/) (2026)
- [S-DiverSe: Spanish Diverse Speech](https://mlsanity.com/paper/2607.03207/) (2026)
- [Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations](https://mlsanity.com/paper/2607.28319/) (2026)
- [Made in Hungary: Comments on the performance of generative language models](https://mlsanity.com/paper/2609.18284/) (2026)

## Abstract (arXiv)

This work introduces Salamandra, a suite of open-source decoder-only large language models available in three different sizes: 2, 7, and 40 billion parameters. The models were trained from scratch on highly multilingual data that comprises text in 35 European languages and code. Our carefully curated corpus is made exclusively from open-access data compiled from a wide variety of sources. Along with the base models, supplementary checkpoints that were fine-tuned on public-domain instruction data are also released for chat applications. Additionally, we also share our preliminary experiments on multimodality, which serve as proof-of-concept to showcase potential applications for the Salamandra family. Our extensive evaluations on multilingual benchmarks reveal that Salamandra has strong capabilities, achieving competitive performance when compared to similarly sized open-source models. We provide comprehensive evaluation results both on standard downstream tasks as well as key aspects related to bias and safety.With this technical report, we intend to promote open science by sharing all the details behind our design choices, data curation strategy and evaluation methodology. In addition to that, we deviate from the usual practice by making our training and evaluation scripts publicly accessible. We release all models under a permissive Apache 2.0 license in order to foster future research and facilitate commercial use, thereby contributing to the open-source ecosystem of large language models.