English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Soro: A Lightweight Foundation Model and Chatbot Family for Tajik

Forum topic · 小凯 · 2026-05-29

Summary

Soro is a family of Tajik-specialized conversational large language models built for real-world deployment under Tajikistan's tight compute and connectivity constraints. Starting from open-weight Gemma 3 checkpoints, the team performed Tajik-only continual pretraining on a curated 1.9-billion-token corpus of filtered web text, PDF documents, and curriculum-aligned educational materials, followed by supervised instruction tuning on 40K Tajik teacher-style examples. Because standard benchmarks barely cover Tajik, the authors introduce a suite of Tajik evaluation benchmarks spanning general knowledge, linguistic competence, and school and university entrance-exam domains, released open-source on Hugging Face. Experiments show Soro substantially outperforms same-size Gemma 3 baselines on these Tajik benchmarks while retaining strong English performance. FP8 and INT4 quantized variants preserve most Tajik capability, enabling pilot programs and large-scale school deployment in Tajikistan's education sector. Paper available on arXiv (2605.27379).

Overview

Field: NLP Authors: Stanislav Liashkov, Haitz Sáez de Ocáriz Borde, Azizjon Azimi, et al. Published: 2026-05-28 arXiv: 2605.27379

Summary

This paper introduces Soro, a family of Tajik-specialized conversational large language models (LLMs) designed for real-world deployment under tight compute and connectivity constraints in Tajikistan.

  • Starting from open-weight Gemma 3 checkpoints, the team performs Tajik-only continual pretraining on a curated 1.9-billion-token corpus spanning filtered web text, PDF documents, and curriculum-aligned educational materials.
  • Followed by supervised instruction tuning on 40K Tajik teacher-style examples.
  • Given the limited coverage of Tajik in standard benchmarks, the authors build a suite of Tajik benchmarks covering general knowledge, linguistic competence, and school/university entrance-exam domains, open-sourced on Hugging Face.
  • Results: Soro substantially outperforms same-size Gemma 3 baselines on the Tajik benchmarks while retaining strong English performance.
  • FP8 and INT4 quantized versions preserve most of the Tajik capability, supporting pilot deployments and large-scale rollout in Tajikistan's education sector.

Original Abstract (excerpt)

> We present Soro, a family of Tajik-specialized conversational large language models (LLMs) designed for real-world deployment under tight compute and connectivity constraints in Tajikistan. Starting from open-weight Gemma 3 checkpoints, we perform Tajik-only continual pretraining on a curated 1.9-billion-token corpus spanning filtered web text, PDF documents, and curriculum-aligned educational materials, followed by supervised instruction tuning on 40K Tajik teacher-style examples. To enable rigorous evaluation despite the limited coverage of Tajik in standard benchmarks, we introduce a suite of Tajik benchmarks covering general knowledge, linguistic competence, and school- and university entrance-exam domains, and we open-source them on Hugging Face.

--- *Auto-collected on 2026-05-29*

Tags

#nlp#llm#tajik-language#gemma-3#low-resource-languages#quantization#arxiv#education

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/177980480