Bharat-Omni-3B 🇮🇳

Made in Bihar, Made for Bharat

India's first truly omni model, fine-tuned for all 22 official Indian languages + dialects. Built on top of Qwen2.5-Omni-3B with Thinker LoRA.

Creator: Adarsh Raj | Rosera, Bihar

✨ Features

Understands & Speaks: Hindi, Bhojpuri, Maithili, Magahi, Bengali, Tamil, Telugu, Marathi, Gujarati, Kannada, Malayalam, Punjabi, Urdu, Assamese, Odia + Hinglish
Omni: Text + Audio + Vision capable (Thinker)
Lightweight LoRA: Only 12.7 MB adapter
Trained for Indian context, culture, and daily conversation

🚀 Usage

from peft import PeftModel
from transformers import AutoModel

base = "Qwen/Qwen2.5-Omni-3B"
model = PeftModel.from_pretrained(base, "adarshraj07/Bharat-Omni-3B")

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for adarshraj07/Bharat-Omni-3B

Base model

Qwen/Qwen2.5-Omni-3B

Adapter

(33)

this model