---
license: apache-2.0
library_name: transformers
tags:
- multilingual
- India
- Hindi
- Gujarati
- English
- SVECTOR
language:
- en
- gu
- hi
- mr
- kn
- pa
- te
- ta
pipeline_tag: text-generation
---

# 🚀 Introducing Akshara-8B: AI for India 🇮🇳✨

We’re proud to unveil **Akshara-8B**, our cutting-edge **AI fleet** built exclusively for India’s diverse linguistic landscape. Akshara is designed to **seamlessly understand and generate text** in multiple Indian languages, making AI more accessible, powerful, and tailored to our nation’s needs.

## 🌍 **What is Akshara?**

Akshara-8B is a **highly optimized distilled version** of SVECTOR’s flagship large-scale AI model (Akshara). While it retains the core intelligence and multilingual capabilities of its parent model, Akshara-8B is specifically designed for **efficiency, speed, and accessibility**.  
It leverages advanced distillation techniques to provide powerful AI performance while being lightweight and scalable. Akshara-8B embodies **SVECTOR’s commitment to bringing cutting-edge AI to India**, ensuring robust support for **India’s diverse languages and applications.** 🚀  

Akshara can fluently understand and generate content in:
✅ **Hindi**  
✅ **Gujarati**  
✅ **Marathi**  
✅ **Tamil**  
✅ **Telugu**  
✅ **Kannada**  
✅ **Punjabi**  
✅ **English**   

## 🔥 **Why Akshara?**
🔹 **Made in India, for  India & Global** 🇮🇳  
🔹 **Optimized for speed and efficiency** ⚡  
🔹 **Seamless multilingual processing** 🗣️  
🔹 **Balanced accuracy and creativity** 🎨  
🔹 **Lightweight and scalable for real-world applications** 🚀  

---

## 🛠️ **Usage Guide**
### Install Dependencies  
```bash
pip install transformers torch
```

### Load the Model
```python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "SVECTOR-CORPORATION/Akshara-8B-Llama-Multilingual-V0.1"

# Load the model
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16).to("cuda")
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)

# Sample input
input_text = "भारत की सबसे बड़ी भाषा कौनसी है?"
input_ids = tokenizer(input_text, return_tensors="pt").to("cuda")

# Generate response
output = model.generate(**input_ids, max_new_tokens=256)
response = tokenizer.decode(output[0], skip_special_tokens=True)

print(response)
```

---

## 💬 **Multi-turn Conversation Support**
Akshara supports **multi-turn, dynamic conversations** across languages.

```python
messages = [
    {"role": "system", "content": "आप Akshara हैं, भारत के लिए बना एक AI, जो हिंदी, गुजराती, मराठी, तमिल, तेलुगु, कन्नड़, पंजाबी और अंग्रेजी में बातचीत कर सकता है।"},
    {"role": "user", "content": "नमस्ते! आप क्या कर सकते हैं?"}
]

input_ids = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")

outputs = model.generate(input_ids, max_new_tokens=256)
response = outputs[0][input_ids.shape[-1]:]
print(tokenizer.decode(response, skip_special_tokens=True))
```

---

## 🌟 **Akshara: Built for the Future of AI in India**  
By embracing India’s linguistic diversity, Akshara represents a major step toward **bridging the AI gap** in our country. Whether it's **education, research, customer service, content creation, or smart automation**, Akshara is here to revolutionize **multilingual AI interactions**.

### **Join us as we shape the future of AI for India! 🇮🇳🚀**

## [Akshara](https://www.svector.co.in/akshara)


```bibtex
@misc{SVECTOR2025Akshara,
  title     = {Akshara: A Multilingual AI Model for India},
  author    = {SVECTOR},
  year      = {2025},
  url       = {https://svector.co.in},
  note      = {Developed by SVECTOR CORPORATION for multilingual AI Model},
}