GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecture

• URL: http://arxiv.org/abs/2506.09440v1
• Date: Wed, 11 Jun 2025 06:46:49 GMT
• Title: GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecture
• Authors: GigaChat team, Mamedov Valentin, Evgenii Kosarev, Gregory Leleytner, Ilya Shchuckin, Valeriy Berezovskiy, Daniil Smirnov, Dmitry Kozlov, Sergei Averkiev, Lukyanenko Ivan, Aleksandr Proshunin, Ainur Israfilova, Ivan Baskov, Artem Chervyakov, Emil Shakirov, Mikhail Kolesov, Daria Khomich, Darya Latortseva, Sergei Porkhun, Yury Fedorov, Oleg Kutuzov, Polina Kudriavtseva, Sofiia Soldatova, Kolodin Egor, Stanislav Pyatkin, Dzmitry Menshykh, Grafov Sergei, Eldar Damirov, Karlov Vladimir, Ruslan Gaitukiev, Arkadiy Shatenov, Alena Fenogenova, Nikita Savushkin, Fedor Minkin,
• Abstract summary: This paper introduces the GigaChat family of Russian large language models (LLMs)<n>We provide a detailed report on the model architecture, pre-training process, and experiments to guide design choices.<n>The paper presents a system demonstration of the top-performing models accessible via an API, a Telegram bot, and a Web interface.
• Score: 24.006981776597147
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative large language models (LLMs) have become crucial for modern NLP research and applications across various languages. However, the development of foundational models specifically tailored to the Russian language has been limited, primarily due to the significant computational resources required. This paper introduces the GigaChat family of Russian LLMs, available in various sizes, including base models and instruction-tuned versions. We provide a detailed report on the model architecture, pre-training process, and experiments to guide design choices. In addition, we evaluate their performance on Russian and English benchmarks and compare GigaChat with multilingual analogs. The paper presents a system demonstration of the top-performing models accessible via an API, a Telegram bot, and a Web interface. Furthermore, we have released three open GigaChat models in open-source (https://huggingface.co/ai-sage), aiming to expand NLP research opportunities and support the development of industrial solutions for the Russian language.

Related papers

• Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modality [74.59049806800176]
  This demo paper highlights the Tevatron toolkit's key features, bridging academia and industry.<n>We showcase a unified dense retriever achieving strong multilingual and multimodal effectiveness.<n>We also release OmniEmbed, to the best of our knowledge, the first embedding model that unifies text, image document, video, and audio retrieval.
  arXiv  Detail & Related papers  (2025-05-05T08:52:49Z)
• xVLM2Vec: Adapting LVLM-based embedding models to multilinguality using Self-Knowledge Distillation [2.9998889086656586]
  We propose an adaptation methodology for Large Vision-Language Models trained on English language data to improve their performance.<n>We introduce a benchmark to evaluate the effectiveness of multilingual and multimodal embedding models.
  arXiv  Detail & Related papers  (2025-03-12T12:04:05Z)
• LLMic: Romanian Foundation Language Model [76.09455151754062]
  We present LLMic, a foundation language model designed specifically for the Romanian Language.<n>We show that fine-tuning LLMic for language translation after the initial pretraining phase outperforms existing solutions in English-to-Romanian translation tasks.
  arXiv  Detail & Related papers  (2025-01-13T22:14:45Z)
• Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian [44.13635168077528]
  Vikhr is a series of bilingual open-source instruction-following LLMs designed specifically for the Russian language.<n>Vikhr features an adapted tokenizer vocabulary and undergoes the continued pre-training and instruction tuning of all weights.<n>The model weights, instruction sets, and code are publicly available.
  arXiv  Detail & Related papers  (2024-05-22T18:58:58Z)
• CMULAB: An Open-Source Framework for Training and Deployment of Natural Language Processing Models [59.91221728187576]
  This paper introduces the CMU Linguistic Linguistic Backend, an open-source framework that simplifies model deployment and continuous human-in-the-loop fine-tuning of NLP models. CMULAB enables users to leverage the power of multilingual models to quickly adapt and extend existing tools for speech recognition, OCR, translation, and syntactic analysis to new languages.
  arXiv  Detail & Related papers  (2024-04-03T02:21:46Z)
• Gl\'orIA - A Generative and Open Large Language Model for Portuguese [4.782288068552145]
  We introduce Gl'orIA, a robust European Portuguese decoder LLM. To pre-train Gl'orIA, we assembled a comprehensive PT-PT text corpus comprising 35 billion tokens from various sources. Evaluation shows that Gl'orIA significantly outperforms existing open PT decoder models in language modeling.
  arXiv  Detail & Related papers  (2024-02-20T12:36:40Z)
• 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)
• Language Models are Universal Embedders [45.8316643119292]
  In the large language model (LLM) revolution, embedding is a key component of various systems.<n>We propose strategies for constructing embedders and introduce a universal evaluation benchmark.<n> Experimental results show that our trained model is proficient at generating good embeddings across languages and tasks.
  arXiv  Detail & Related papers  (2023-10-12T11:25:46Z)
• A Family of Pretrained Transformer Language Models for Russian [31.1608981359276]
  This paper introduces a collection of 13 Russian Transformer LMs, which spans encoder (ruBERT, ruRoBERTa, ruELECTRA), decoder (ruGPT-3), and encoder-decoder (ruT5, FRED-T5) We provide a report on the model architecture design and pretraining, and the results of evaluating their generalization abilities on Russian language understanding and generation datasets and benchmarks.
  arXiv  Detail & Related papers  (2023-09-19T21:07:52Z)
• 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)
• Generalizing Multimodal Pre-training into Multilingual via Language Acquisition [54.69707237195554]
  English-based Vision-Language Pre-training has achieved great success in various downstream tasks. Some efforts have been taken to generalize this success to non-English languages through Multilingual Vision-Language Pre-training. We propose a textbfMultitextbfLingual textbfAcquisition (MLA) framework that can easily generalize a monolingual Vision-Language Pre-training model into multilingual.
  arXiv  Detail & Related papers  (2022-05-29T08:53:22Z)
• mGPT: Few-Shot Learners Go Multilingual [1.4354798873010843]
  This paper introduces two autoregressive GPT-like models with 1.3 billion and 13 billion parameters trained on 60 languages. We reproduce the GPT-3 architecture using GPT-2 sources and the sparse attention mechanism. The resulting models show performance on par with the recently released XGLM models by Facebook.
  arXiv  Detail & Related papers  (2022-04-15T13:02:33Z)
• Scribosermo: Fast Speech-to-Text models for German and other Languages [69.7571480246023]
  This paper presents Speech-to-Text models for German, as well as for Spanish and French with special features. They are small and run in real-time on microcontrollers like a RaspberryPi. Using a pretrained English model, they can be trained on consumer-grade hardware with a relatively small dataset.
  arXiv  Detail & Related papers  (2021-10-15T10:10:34Z)

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.