Downloads · 30 days
0
Bharat-Omni-3B
adarshraj07/Bharat-Omni-3B
Bharat-Omni-3B is a machine learning model from adarshraj07. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
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.
Access
Public
Updated Aug 24, 2026
Repo size
12.7 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors12.7 MB · 100%
At a glance
- License
- apache-2.0
- Access
- Public
- Created
- Aug 24, 2026
- Updated
- Aug 24, 2026
- SHA
- 0ba44936
Base models
Model card
From the Hugging Face model README
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")
- License
- apache-2.0
- Languages
- hi, bho, mai, mag, bn, ta
- Created
- Aug 24, 2026
- Updated
- Aug 24, 2026