---
base_model: unsloth/llama-3.1-8b-bnb-4bit
tags:
- text-generation-inference
- transformers
- unsloth
- llama
license: apache-2.0
language:
- en
---
# 🚀 NextBharat V2 Final

**NextBharat V2** is a fine-tuned version of Llama-3.1-8B, specifically optimized for regional Indian languages and student-centric queries. Developed at **NextMatrix Lab**, this model aims to bridge the language gap for students in Tier 2 and Tier 3 cities.

### ✨ Key Features:
* **Regional Support:** Trained to understand and respond in multiple Indian regional contexts.
* **Student Focused:** Optimized for competitive exam guidance (SSC, Railway, etc.) and technical subjects like Compiler Design and DBMS.
* **Lightweight & Fast:** Finetuned using Unsloth for 4-bit quantization, making it efficient for inference.

### 🛠️ Technical Details:
- **Base Model:** unsloth/llama-3.1-8b-bnb-4bit
- **Training Method:** LoRA (Rank 16)
- **Developer:** Anoop Singh (Founder, NextMatrix Lab)

### 📖 How to Use:
```python
from unsloth import FastLanguageModel
model, tokenizer = FastLanguageModel.from_pretrained("Anoopsingh53/NextBharat-V2-Final")
# Uploaded finetuned  model

- **Developed by:** Anoopsingh53
- **License:** apache-2.0
- **Finetuned from model :** unsloth/llama-3.1-8b-bnb-4bit

This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)