PARAM-1 BharatGen 2.9B Model

TL;DR

PARAM-1 is a 2.9B parameter language model specifically designed to represent and process Indian languages and dialects, emphasizing linguistic diversity and cultural relevance in its architecture and training data.

Contribution

It introduces a culturally and linguistically focused Indian language model with equitable representation, adapted tokenization, and diverse benchmarks, setting a new standard for inclusive foundation models.

Findings

Achieves strong performance on Indian language tasks.

Demonstrates robustness in code-mixed and socio-linguistic contexts.

Provides a blueprint for equitable multilingual model design.

Abstract

Large Language Models (LLMs) have emerged as powerful general-purpose reasoning systems, yet their development remains dominated by English-centric data, architectures, and optimization paradigms. This exclusionary design results in structural under-representation of linguistically diverse regions such as India, where over 20 official languages and 100+ dialects coexist alongside phenomena like code-switching and diglossia. We introduce PARAM-1, a 2.9B parameter decoder-only, text-only language model trained from scratch with an explicit architectural and linguistic focus on Indian diversity. PARAM-1 is trained on a bilingual dataset consisting of only Hindi and English, constructed with a strong focus on fact-rich, high-quality content. It is guided by three core principles: equitable representation of Indic languages through a 25% corpus allocation; tokenization fairness via a SentencePiece tokenizer adapted to Indian morphological structures; and culturally aligned evaluation benchmarks across IndicQA, code-mixed reasoning, and socio-linguistic robustness tasks. By embedding diversity at the pretraining level-rather than deferring it to post-hoc alignment-PARAM-1 offers a design-first blueprint for equitable foundation modeling. Our results demonstrate that it serves as both a competent general-purpose model and a robust baseline for India-centric applications.