Ganga-2-1B
The first pre-trained Hindi model by any academic research lab in India 🇮🇳!
About Model
Project Unity is an initiative to address India's linguistic diversity and richness by creating a comprehensive resource covering the country's major languages. We strive to achieve state-of-the-art performance in understanding and generating text in Indian languages. To achieve this, we train models on the monolingual regional languages of India. Our first release is the Ganga-1B model, which has been trained on a large dataset of public domain web-crawled Hindi language data, including news articles, web documents, books, government publications, educational materials, and social media conversations (filtered for quality). Additionally, the dataset has been further curated by native Indian speakers to ensure high quality. Significantly, the Ganga-2-1B model outperforms existing open-source models that support Indian languages, even at sizes of up to 7 billion parameters.
Developed by: Lingo Research Group at IIT Gandhinagar
Model type: Autoregressive Language Model
Language(s): Bilingual (Primary: Hindi [hi], Secondary: English [en])
The instruct tunned model Ganga-2-1b trained on a monolingual Hindi language dataset as part of Project Unity. We propose the name Ganga 🌊 to honor the longest river flowing through the Hindi-speaking region of India 🇮🇳.
- Precision: BFloat16
- Context Length: 2,048
- Learning Rate: 4e-4
- Optimizer: AdamW
- LR Scheduler: Cosine
Model Architecture and Objective:
Ganga-2-1b is a decoder-only transformer model featuring the following specifications:
- Layers: 16
- Attention heads: 32
- Embedding dimension: 2,048
- Vocabulary size: 32,768
- Sliding window: 1024
- Intermediate dimension: 7,168
Results:
Tokenizers Results:
| Model | Fertility |
|---|---|
| Ganga-2-1b | 1.12 |
| Pragna-1b | 1.58 |
| Bloom-1b1 | 1.27 |
| Bloom-1b7 | 1.27 |
| Gemma-2b | 1.89 |
| Bloom-3b | 1.27 |
| Airavata-7b | 1.69 |
| Sarvam-2b | 1.38 |
| Model | PPLSangraha Dataset |
|---|---|
| Ganga-2-1b | 8.09 |
| Ganga-1b | 15.82 |
| Pragna-1b | 9.37 |
| Bloom-1b1 | 17.49 |
| Bloom-1b7 | 14.28 |
| Gemma-2b | 31.01 |
| Bloom-3b | 12.82 |
| OpenHathi-7B | 25.73 |
| Airavata-7b | 38.24 |
| Sarvam-2b | 10.31 |
Recommendations ‼️
This model described is a research preview and is under ongoing iterative updations, and as such, it only provides limited safety measures. Additionally, it may generate offensive content. It is strictly prohibited to use the model for any illegal, harmful, violent, racist, or sexual purposes.
Ganga-2-1B
Metadata
Apache 2.0
Aamod Thakur, Mayank singh
Large Language Models
Transformers
Open
Science, Technology and Research
20/08/25 05:43:32
1.88 GB
Activity Overview
1
17 
287 
1.88 GB
Tags
- Text Generation
License Control
Apache 2.0
Version Control
Version 1(1.88 GB)
- admin·7 month(s) ago
.DS_Store
.gitattributes
config.json
generation_config.json
model.safetensors
special_tokens_map.json
tokenizer_config.json
tokenizer.json
More Models from IITGN
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.