Indic LM Platform

In plain words

AyurParam-2.9B is a Ayurveda domain-specialized, bilingual large language model built by the BharatGen team at IIT Bombay's Technology Innovation Hub.

How to use it

Before you start

Prerequisites required to run the model locally

To run Param 1 model locally on your computer, the following requirements must be met:

Install and set up Ollama.
Ensure your computer has enough RAM to run the model you plan to download.

For 3B models: Minimum 8 GB of RAM.
For 7B–8B models: Minimum 16 GB of RAM.
For 13B–32B models: Minimum 32 GB of RAM.

Quantised model: It is recommended to use 4-bit Quantized, K-measurement, Small model format. Easy to download and to run your system.
Storage: 5 to 20 GB of free SSD space to store downloaded model files.
Interface: Terminal or command line utility to run basic startup prompts.

No technical setup needed — anyone can try AyurParam using below mentioned steps.

Downloading the AyurParam GGUF file

Go to the AayurParam 1 GGUF file on Hugging Face. Click the copy icon next to the repository name to copy the model path. (See image below.)

Run the model in your terminal

Open a terminal window and run the following command and paste the copied GGUF repository as mentioned below:

ollama run hf.co/PASTE_THE_COPIED_HERE

Press Enter.

Note: After pasting the repository, your command will look like this:

ollama run hf.co/Prady029/AyurParam-2.9b-it-gguf

Wait for the model to load

Ollama will download and initialise the model. Once ready, you'll see the following prompt:

>>> Send a message (/? for help)

Start chatting

Type your message at the prompt and press Enter to interact with the model.

Exit the chat

To end the session, type:

/bye

Then press Enter.

Languages & scripts supported

Works in these languages, in both native script and Roman typing.

English Englishहिन्दी Hindi+ Roman & code-mixed

Strengths & limits

An honest look at what it does well and where it struggles.

Good at

✓Domain Specialization

✓Bilingual Capability

Where it struggles

!Lack of Multimodality

!Clinical Safety

Technical details & licence

Training dataTrained from scratch AyurParam was fine-tuned using Supervised Fine-Tuning (SFT) via the Hugging Face TRL framework. Custom bilingual instruction templates were developed to better support both single-turn and multi-turn Ayurvedic instruction-following across English and Hindi.

SizeDecoder-only transformer, 32 layers, 2048 hidden size, grouped-query attention, SwiGLU activation, and rotary positional embeddings, with a custom SentencePiece tokenizer.

LicenceThe 2.9B base/instruct checkpoints are freely usable, including commercially, under Apache 2.0 — though positioned by BharatGen as an early-stage research checkpoint rather than a production-ready model.

Commercial costFree to self-host (open weights)

Version historyParam-1-2.9B (base) · July 2025 — Initial from-scratch bilingual foundation modelParam-1-2.9B-Instruct · July 2025 — Early-stage instruction-tuned checkpoint

About the maker

Who builds and maintains AyurParam.

BharatGen AI

1 models

BharatGen AI is a government-funded, multi-institution research consortium anchored by IIT Bombay, bringing together IIT Madras, IIT Kanpur, IIT Hyderabad, IIM Indore, and several other IITs and IIITs under the National Mission on Interdisciplinary Cyber-Physical Systems. It released Param-1, a 2.9-billion-parameter bilingual English-Hindi foundation model trained with a far higher share of Indic-language data than most global models of similar size.

View their models →See all organisations →