AI News HubLIVE
原文

Soro: A Lightweight Foundation Model and Chatbot for Tajik

Soro is a family of Tajik-specialized conversational LLMs built on Gemma 3, using 1.9B token Tajik continual pretraining and 40K instruction tuning examples. It substantially outperforms same-size Gemma 3 on Tajik benchmarks while retaining English performance. FP8/INT4 quantization preserves gains for edge deployment. An education pilot is underway in Tajikistan.

Article intelligence

InvestorsAdvanced

Key points

  • Based on Gemma 3, with 1.9B token Tajik continual pretraining and 40K instruction tuning examples.
  • Substantially outperforms same-size Gemma 3 on Tajik benchmarks, retains English performance.
  • FP8/INT4 quantization preserves most Tajik gains, reduces memory for edge deployment.
  • Education sector pilot in Tajikistan, planned scale-out to schools.

Why it matters

This matters because based on Gemma 3, with 1.9B token Tajik continual pretraining and 40K instruction tuning examples.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.27379] Soro: A Lightweight Foundation Model and Chatbot for Tajik

[Submitted on 9 Apr 2026]

Title:Soro: A Lightweight Foundation Model and Chatbot for Tajik

View a PDF of the paper titled Soro: A Lightweight Foundation Model and Chatbot for Tajik, by Stanislav Liashkov and 5 other authors

View PDF

Abstract: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. Across these Tajik benchmarks, Soro substantially outperforms same-size Gemma 3 baselines while retaining strong English performance on standard datasets. We further show that FP8 and INT4 quantization of Soro preserves most Tajik-language gains while reducing memory requirements for edge deployment, supporting an ongoing education-sector pilot and planned scale-out across schools in Tajikistan.

Subjects:

Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

Cite as: arXiv:2605.27379 [cs.AI]

(or arXiv:2605.27379v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2605.27379

arXiv-issued DOI via DataCite

Submission history

From: Bonu Boboeva [view email] [v1] Thu, 9 Apr 2026 15:04:32 UTC (3,650 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Soro: A Lightweight Foundation Model and Chatbot for Tajik, by Stanislav Liashkov and 5 other authors

View PDF

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-05

Change to browse by:

cs cs.CL

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)