Update README.md

README.md

@@ -45,12 +45,12 @@ library_name: transformers
 ---
 
 
-![Banner](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEg5Qto7D0vUhnfdVq5JQ0yIaqkrj70TiM6Q8f5UfkX__Ht1Ad2KSeshb6SPHa7Ri8dQFnWGXknOckqCjgIlf6sOQge_1BYzoAT6YQMgQSjgrsA0m8YNSTGirUY5JA-zTarCIKelkYfJdS1KYrkR0PT46TfqZaMyS7W1SzhUsbHCPdKm09ftRo4znKbP8Mc/s4000/small.jpg)
+![Banner](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEimiqZpB7hWFuvJz_GA-3Rj0ZbYpqS-6UYVt2Ok7i4I1c3muCjjkOHne58IS9MKxIppSTvDAnqViyT9qQAgywjLYDmhqFoqoaThu9Ce97gJzmwK2tGZb0JOQd3A8EYFSzyPaeasdiTZU7KdVhoPXKbOO_N02XB5vL4cX5UpBE17AiovMGgVE1JqoT2kZHg/s16000/small.jpg)
 
 # 🧠 NeuroBERT-Small — Compact BERT for Smarter NLP on Low-Power Devices 🔋
 
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
-[![Model Size](https://img.shields.io/badge/Size-~45MB-blue)](#)
+[![Model Size](https://img.shields.io/badge/Size-~50MB-blue)](#)
 [![Tasks](https://img.shields.io/badge/Tasks-MLM%20%7C%20Intent%20Detection%20%7C%20Text%20Classification%20%7C%20NER-orange)](#)
 [![Inference Speed](https://img.shields.io/badge/Optimized%20For-Low--Power%20Devices-green)](#)
 
@@ -72,14 +72,14 @@ library_name: transformers
 - 🙏 [Credits](#credits)
 - 💬 [Support & Community](#support--community)
 
-![Banner](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEijUXvkohDsomgIveUNAcDVdz2gRXxyeJ7wQEna-ZwB8U3kpgSq7_PMthS7eJlLbf4ZS6rVpAmuXbfYz3BJIAcsMnr65EqWRpcZXsHYdygPhqmZvf9xbVZorcO_EkRQfmGDxu6B61lZoQlm9UVZivrt-2ef_RgvUwPixWuidH9PWjskQUPcDl1lLlfp6Zg/s6250/small-help.jpg)
+![Banner](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEjDTnQ3z0BhHVEVOLVwZ4heya2dOK68R6a4pgRxsSHuhyphenhyphencpvZr2Sjc2rmdR3Xrs2d2V1wKUtbDkI9tcE0KJoLQ2MxCwtqej7SyGxj7jHDqg0nVUFmnxN-WxWo4cAjoYdSEtclts8LHw3MdnceR1GafZj1VXeM8CxaOiktSeSOo54Bcz8M7lzLhzM7Ur45k/s16000/small-help.jpg)
 
 ## Overview
 
-`NeuroBERT-Small` is a **compact** NLP model derived from **google/bert-base-uncased**, optimized for **real-time inference** on **low-power devices**. With a quantized size of **~45MB** and **~20M parameters**, it delivers robust contextual language understanding for resource-constrained environments like mobile apps, wearables, microcontrollers, and smart home devices. Designed for **low-latency**, **offline operation**, and **smarter NLP**, it’s perfect for applications requiring intent recognition, classification, and real-time predictions in privacy-first settings with limited connectivity.
+`NeuroBERT-Small` is a **compact** NLP model derived from **google/bert-base-uncased**, optimized for **real-time inference** on **low-power devices**. With a quantized size of **~50MB** and **~20M parameters**, it delivers robust contextual language understanding for resource-constrained environments like mobile apps, wearables, microcontrollers, and smart home devices. Designed for **low-latency**, **offline operation**, and **smarter NLP**, it’s perfect for applications requiring intent recognition, classification, and real-time predictions in privacy-first settings with limited connectivity.
 
 - **Model Name**: NeuroBERT-Small
-- **Size**: ~45MB (quantized)
+- **Size**: ~50MB (quantized)
 - **Parameters**: ~20M
 - **Architecture**: Compact BERT (6 layers, hidden size 256, 4 attention heads)
 - **Description**: Standard 6-layer, 256-hidden
@@ -87,7 +87,7 @@ library_name: transformers
 
 ## Key Features
 
-- ⚡ **Compact Design**: ~45MB footprint fits low-power devices with limited storage.
+- ⚡ **Compact Design**: ~50MB footprint fits low-power devices with limited storage.
 - 🧠 **Robust Contextual Understanding**: Captures deep semantic relationships with a 6-layer architecture.
 - 📶 **Offline Capability**: Fully functional without internet access.
 - ⚙️ **Real-Time Inference**: Optimized for CPUs, mobile NPUs, and microcontrollers.
@@ -101,7 +101,7 @@ Install the required dependencies:
 pip install transformers torch
 ```
 
-Ensure your environment supports Python 3.6+ and has ~45MB of storage for model weights.
+Ensure your environment supports Python 3.6+ and has ~50MB of storage for model weights.
 
 ## Download Instructions
 
@@ -297,7 +297,7 @@ NeuroBERT-Small is designed for **low-power devices** in **edge and IoT scenario
 ## Hardware Requirements
 
 - **Processors**: CPUs, mobile NPUs, or microcontrollers (e.g., Raspberry Pi, ESP32-S3)
-- **Storage**: ~45MB for model weights (quantized for reduced footprint)
+- **Storage**: ~50MB for model weights (quantized for reduced footprint)
 - **Memory**: ~100MB RAM for inference
 - **Environment**: Offline or low-connectivity settings
 
@@ -395,7 +395,7 @@ To adapt NeuroBERT-Small for custom IoT tasks (e.g., specific smart home command
 
 | Model           | Parameters | Size   | Edge/IoT Focus | Tasks Supported         |
 |-----------------|------------|--------|----------------|-------------------------|
-| NeuroBERT-Small | ~20M       | ~45MB  | High           | MLM, NER, Classification |
+| NeuroBERT-Small | ~20M       | ~50MB  | High           | MLM, NER, Classification |
 | NeuroBERT-Mini  | ~10M       | ~35MB  | High           | MLM, NER, Classification |
 | NeuroBERT-Tiny  | ~5M        | ~15MB  | High           | MLM, NER, Classification |
 | DistilBERT      | ~66M       | ~200MB | Moderate       | MLM, NER, Classification |