Indian Flag
Government Of India
A-
A
A+
Home/Models/BharatGen - Param 1 Indic-Scale Bilingual Foundation Model
ownerKundeshwar Vijay Pundalik
organizationBharatGen
ORGANISATION

BharatGen - Param 1 Indic-Scale Bilingual Foundation Model

Param1 is a 2.9 billion parameter language model pretrained on English and Hindi, designed for text completion.

About Model

Param 1 is a 2.9-billion parameter foundation model developed for English and Hindi, capable for text generation and completion. Pretrained on high-quality, culturally rich datasets from diverse Indian domains approximately on 5 Trillion Tokens combined for English and Hindi, it delivers better performance on bilingual tasks while maintaining computational efficiency, outperforming several models of similar size and task scope on standard benchmarks. Param 1 is developed by BharatGen: A Suite of Generative AI Tech for India.
For any queries, please visit https://bharatgen.discourse.group/invites/BcouFsKk4g

BharatGen - Param 1 Indic-Scale Bilingual Foundation Model

Metadata Metadata

MIT

Kundeshwar Pundalik, Piyush Sawarkar, Vedant Goswami, Ajay Nagpal, Smita Gautam, Bhagwan Panditi, Adugani Vanjari Akanksh, Pankaj Singh, Rishi Bal, Prof. Rohit Saluja, Prof. Ganesh Ramakrishnan

Text Generation

Transformers

Open

BharatGen

Science, Technology and Research

18/07/25 08:53:23

Kundeshwar Vijay Pundalik

13.79 GB

config_parambharatgen.py ( 1.92 KB )

To preview this file, you need to be a registered user. Please complete the registration process to gain access and continue viewing the content.

Activity Overview Activity Overview

  • Downloads4
  • Downloads 726
  • File Size 5.35 GB
  • Views 20,984

Tags Tags

  • Large Language Model

License Control License Control

MIT

Version Control Version Control

FolderVersion 2(5.35 GB)
  • admin·3 month(s) ago
    • undefined
      config_parambharatgen.py
    • application/json
      config.json
    • application/json
      generation_config.json
    • undefined
      model.safetensor
    • undefined
      modeling_parambharatgen.py
    • text/markdown
      README.md
    • application/json
      special_tokens_map.json
    • application/json
      tokenizer_config.json
    • application/json
      tokenizer.json

More Models from BharatGen More Models from BharatGen

sooktam2
Sooktam-2 is a multilingual Indic Text-to-Speech model by BharatGen supporting 12 languages including Hindi, Marathi, Tamil, Telugu, Bengali, Urdu, Punjabi and Indian English. It enables high-quality speech synthesis with reference-guided voice conditioning, preserving speaker voice, accent and prosody for natural and expressive generation.
tts
Text to Speech
sooktam2
f5-tts
indic
Multilingual
  • See Upvoters0
  • Downloads22
  • File Size0
  • Views226
Updated 2 month(s) ago
BHARATGEN
View Details
share
Shrutam-2
Shrutam-2 is a LLM based automatic speech recognition system for 12 major Indian languages. It bridges a Conformer speech encoder with a pretrained LLM decoder through a Mixture-of-Experts (MoE) projection layer, enabling high-quality, prompt-controllable transcription across diverse Indic languages.
Speech-to-Text
Automatic Speech Recognition
  • See Upvoters0
  • Downloads3
  • File Size8.37 GB
  • Views227
Updated 3 month(s) ago
BHARATGEN
View Details
share
Param-1-5B
Param-1-5B is a bilingual (English–Hindi) large language model developed under the Param-1 family. With 5 billion parameters, this model extends the capabilities of Param-1-2.9B by incorporating enhanced mathematical reasoning and code understanding/generation. The model is pretrained from scratch and designed to serve as a strong foundation for downstream tasks such as mathematical problem solving, and code-related understanding / generation.
pretrained
  • See Upvoters0
  • Downloads1
  • File Size10.42 GB
  • Views140
Updated 3 month(s) ago
BHARATGEN
View Details
share
Param-1-Instruct
BharatGen introduces the early checkpoint of SFT (Supervised Fine-Tuned) for Param 1, a bilingual language model trained from scratch in English and Hindi. With 2.9 billion parameters, this checkpoint builds upon the pretraining phase and serves as a foundation for more downstream tasks, safety testing, and customization.
QnA
Instruction-Tuning
Model Fine-Tuning
  • See Upvoters0
  • Downloads17
  • File Size5.36 GB
  • Views135
Updated 3 month(s) ago
BHARATGEN
View Details
share
BharatGen - Param 1 Indic-Scale Bilingual Foundation Model
Param1 is a 2.9 billion parameter language model pretrained on English and Hindi, designed for text completion.
Large Language Model
  • See Upvoters4
  • Downloads726
  • File Size13.79 GB
  • Views20,984
Updated 3 month(s) ago
BHARATGEN
View Details
share
Param2-17B-Thinking
BharatGen presents Param-2-17B-MoE-A2.4B, a large-scale Mixture-of-Experts (MoE) language model designed to deliver high model capacity while retaining the inference efficiency of a much smaller dense model. It uses a Hybrid MoE architecture with 17B total parameters, while activating only 2.4B parameters per token.
Mixture of Experts
pretrained
Multilingual Text
  • See Upvoters1
  • Downloads73
  • File Size57.29 GB
  • Views2,947
Updated 5 month(s) ago
BHARATGEN
View Details
share
BharatGen Multilingual TTS - Sooktam2
Sooktam-2 is a multilingual Indic Text-to-Speech model by BharatGen supporting 12 languages including Hindi, Marathi, Tamil, Telugu, Bengali, Urdu, Punjabi and Indian English. It enables high-quality speech synthesis with reference-guided voice conditioning, preserving speaker voice, accent and prosody for natural and expressive generation.
Text-to-Speech
Audio Synthesis
sooktam2
Multilingual Speech
multilingual-TTS
  • See Upvoters0
  • Downloads23
  • File Size1.25 GB
  • Views1,985
Updated 5 month(s) ago
BHARATGEN
View Details
share
BharatGen - Param-1-7B-MoE Advancing Multilingual GenAI for India
Param-1-7B-MoE is a multilingual large language model developed under the Param-1 family as part of BharatGen – A Suite of Generative AI Technologies for India. With 7 billion parameters and a Mixture of Experts (MoE) architecture, the model is designed to better understand and generate text across English, Hindi, and 14 additional Indian languages. The model is pretrained from scratch with a strong focus on linguistic diversity, cultural context, and large-scale multilingual representation.
safetensors
region:us
mixtral
  • See Upvoters1
  • Downloads88
  • File Size0
  • Views1,704
Updated 7 month(s) ago
BHARATGEN
View Details
share
BharatGen-AgriParam
Large language model fine-tuned from Param-1-2.9B-Instruct on a high-quality, India-centric agriculture dataset.
Multiturn
QnA
  • See Upvoters0
  • Downloads48
  • File Size0
  • Views482
Updated 8 month(s) ago
BHARATGEN
View Details
share
BharatGen-FinanceParam
large language model fine-tuned from Param-1-2.9B-Instruct on a high-quality finance dataset.
Multiturn
QnA
  • See Upvoters0
  • Downloads44
  • File Size0
  • Views575
Updated 8 month(s) ago
BHARATGEN
View Details
share

© 2026 - Copyright AIKosh. All rights reserved.