Salamandra Technical Report

• URL: http://arxiv.org/abs/2502.08489v2
• Date: Thu, 13 Feb 2025 17:33:24 GMT
• Title: Salamandra Technical Report
• Authors: Aitor Gonzalez-Agirre, Marc Pàmies, Joan Llop, Irene Baucells, Severino Da Dalt, Daniel Tamayo, José Javier Saiz, Ferran Espuña, Jaume Prats, Javier Aula-Blasco, Mario Mina, Iñigo Pikabea, Adrián Rubio, Alexander Shvets, Anna Sallés, Iñaki Lacunza, Jorge Palomar, Júlia Falcão, Lucía Tormo, Luis Vasquez-Reina, Montserrat Marimon, Oriol Pareras, Valle Ruiz-Fernández, Marta Villegas,
• Abstract summary: Salamandra is a suite of 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.
• Score: 27.291503904557263
• License:
• Abstract: 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.

Related papers

• Tradutor: Building a Variety Specific Translation Model [3.976102757693942]
  We introduce the first open-source translation model specifically tailored for European Portuguese. Our best model surpasses existing open-source translation systems for Portuguese. By making our dataset, models, and code publicly available, we aim to support and encourage further research.
  arXiv  Detail & Related papers  (2025-02-20T09:20:59Z)
• Data-Augmentation-Based Dialectal Adaptation for LLMs [26.72394783468532]
  This report presents GMUNLP's participation to the Dialect-Copa shared task at VarDial 2024. The task focuses on evaluating the commonsense reasoning capabilities of large language models (LLMs) on South Slavic micro-dialects. We propose an approach that combines the strengths of different types of language models and leverages data augmentation techniques to improve task performance.
  arXiv  Detail & Related papers  (2024-04-11T19:15:32Z)
• Dolma: an Open Corpus of Three Trillion Tokens for Language Model Pretraining Research [139.69207791947738]
  Dolma is a three-trillion-token English corpus built from a diverse mixture of web content, scientific papers, code, public-domain books, social media, and encyclopedic materials. We document Dolma, including its design principles, details about its construction, and a summary of its contents. We present analyses and experimental results on intermediate states of Dolma to share what we have learned about important data curation practices.
  arXiv  Detail & Related papers  (2024-01-31T20:29:50Z)
• YAYI 2: Multilingual Open-Source Large Language Models [53.92832054643197]
  We propose YAYI 2, including both base and chat models, with 30 billion parameters. YAYI 2 is pre-trained from scratch on a multilingual corpus which contains 2.65 trillion tokens filtered by our pre-training data processing pipeline. The base model is aligned with human values through supervised fine-tuning with millions of instructions and reinforcement learning from human feedback.
  arXiv  Detail & Related papers  (2023-12-22T17:34:47Z)
• Traces of Memorisation in Large Language Models for Code [16.125924759649106]
  Large language models for code are commonly trained on large unsanitised corpora of source code scraped from the internet. We compare the rate of memorisation with large language models trained on natural language. We find that large language models for code are vulnerable to data extraction attacks, like their natural language counterparts.
  arXiv  Detail & Related papers  (2023-12-18T19:12:58Z)
• Cross-Lingual NER for Financial Transaction Data in Low-Resource Languages [70.25418443146435]
  We propose an efficient modeling framework for cross-lingual named entity recognition in semi-structured text data. We employ two independent datasets of SMSs in English and Arabic, each carrying semi-structured banking transaction information. With access to only 30 labeled samples, our model can generalize the recognition of merchants, amounts, and other fields from English to Arabic.
  arXiv  Detail & Related papers  (2023-07-16T00:45:42Z)
• Multi-lingual Evaluation of Code Generation Models [82.7357812992118]
  We present new benchmarks on evaluation code generation models: MBXP and Multilingual HumanEval, and MathQA-X. These datasets cover over 10 programming languages. We are able to assess the performance of code generation models in a multi-lingual fashion.
  arXiv  Detail & Related papers  (2022-10-26T17:17:06Z)
• Towards Best Practices for Training Multilingual Dense Retrieval Models [54.91016739123398]
  We focus on the task of monolingual retrieval in a variety of typologically diverse languages using one such design. Our study is organized as a "best practices" guide for training multilingual dense retrieval models.
  arXiv  Detail & Related papers  (2022-04-05T17:12:53Z)
• A New Generation of Perspective API: Efficient Multilingual Character-level Transformers [66.9176610388952]
  We present the fundamentals behind the next version of the Perspective API from Google Jigsaw. At the heart of the approach is a single multilingual token-free Charformer model. We demonstrate that by forgoing static vocabularies, we gain flexibility across a variety of settings.
  arXiv  Detail & Related papers  (2022-02-22T20:55:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.