Metadata-Version: 2.4
Name: ecotransformers
Version: 0.1.16
Summary: Optimize LLM outputs and track emissions
Home-page: https://github.com/viji123450/ecotransformers
Author: 
Author-email: 
License: MIT
Requires-Python: >=3.8
Description-Content-Type: text/markdown
License-File: LICENCE
Requires-Dist: torch>=1.13.0
Requires-Dist: transformers>=4.30.0
Requires-Dist: codecarbon>=2.2.2
Requires-Dist: evaluate>=0.4.0
Requires-Dist: numpy>=1.24.0
Requires-Dist: rouge_score>=0.1.2
Requires-Dist: nltk>=3.8.0
Requires-Dist: absl-py>=1.4.0
Dynamic: description
Dynamic: description-content-type
Dynamic: home-page
Dynamic: license
Dynamic: license-file
Dynamic: requires-dist
Dynamic: requires-python
Dynamic: summary

# 🌱 AI Transformer Optimizer with CO₂ Tracking

[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](./LICENSE)
[![Python](https://img.shields.io/badge/python-3.8%2B-blue)](https://www.python.org/)
[![Transformers](https://img.shields.io/badge/Transformers-HuggingFace-orange)](https://huggingface.co/docs/transformers/index)
[![CodeCarbon](https://img.shields.io/badge/CO₂-Tracked-green)](https://mlco2.github.io/codecarbon/)

This package provides an **easy wrapper for Transformer-based models** with:
- ✅ **Baseline vs Optimized inference** comparison  
- ✅ **Self-pruning** (removing near-zero weights)  
- ✅ **Self-freezing** (zeroing inactive activations)  
- ✅ **Perplexity, BLEU, ROUGE metrics**  
- ✅ **CO₂ emissions tracking** (powered by [CodeCarbon](https://mlco2.github.io/codecarbon/))  

---

## 📦 Installation

Clone this repo and install dependencies:

```bash
git clone https://github.com/yourusername/transformer-optimizer.git
cd transformer-optimizer
pip install -r requirements.txt
