boltuix commited on
Commit
13c5cb1
·
verified ·
1 Parent(s): 1e24ba3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -46,7 +46,8 @@ library_name: transformers
46
 
47
  ![Banner](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh5CHabe8dWLvdk4z8CWUXZu-Pe154Gv3u6PzRUKT4YY7pBDpmhYvlkoWHLixc77wZ4ohQ72hD02Ce064xO79kRKNtiinyNA1oFJnhnTsbQYPyQyB-AKlDmB9FBeqBex24SAe5rF8CvW4hfLgxMsq7h8wZCasP5-0PyFOCoYL7r-9mOH7Sowyn2cTLbvWM/s16000/banner.jpg)
48
 
49
- # 🧠 NeuroBERT-Mini — Lightweight BERT for Edge & IoT 🚀
 
50
 
51
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
52
  [![Model Size](https://img.shields.io/badge/Size-~35MB-blue)](#)
@@ -75,7 +76,7 @@ library_name: transformers
75
 
76
  ## Overview
77
 
78
- `NeuroBERT-Mini` is a **lightweight** NLP model derived from **google/bert-base-uncased**, optimized for **real-time inference** on **edge and IoT devices**. With a quantized size of **~35MB** and **~7M parameters**, it delivers efficient contextual language understanding for resource-constrained environments like mobile apps, wearables, microcontrollers, and smart home devices. Designed for **low-latency** and **offline operation**, it’s ideal for privacy-first applications with limited connectivity.
79
 
80
  - **Model Name**: NeuroBERT-Mini
81
  - **Size**: ~35MB (quantized)
@@ -394,8 +395,8 @@ To adapt NeuroBERT-Mini for custom IoT tasks (e.g., specific smart home commands
394
 
395
  | Model | Parameters | Size | Edge/IoT Focus | Tasks Supported |
396
  |-----------------|------------|--------|----------------|-------------------------|
397
- | NeuroBERT-Mini | ~7M | ~35MB | High | MLM, NER, Classification |
398
- | NeuroBERT-Tiny | ~4M | ~15MB | High | MLM, NER, Classification |
399
  | DistilBERT | ~66M | ~200MB | Moderate | MLM, NER, Classification |
400
  | TinyBERT | ~14M | ~50MB | Moderate | MLM, Classification |
401
 
 
46
 
47
  ![Banner](https://blogger.googleusercontent.com/img/b/R29vZ2xl/AVvXsEh5CHabe8dWLvdk4z8CWUXZu-Pe154Gv3u6PzRUKT4YY7pBDpmhYvlkoWHLixc77wZ4ohQ72hD02Ce064xO79kRKNtiinyNA1oFJnhnTsbQYPyQyB-AKlDmB9FBeqBex24SAe5rF8CvW4hfLgxMsq7h8wZCasP5-0PyFOCoYL7r-9mOH7Sowyn2cTLbvWM/s16000/banner.jpg)
48
 
49
+ # 🧠 NeuroBERT-Mini — Fast BERT for Edge AI, IoT & On-Device NLP 🚀
50
+ ⚡ Built for low-latency, lightweight NLP tasks — perfect for smart assistants, microcontrollers, and embedded apps!
51
 
52
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
53
  [![Model Size](https://img.shields.io/badge/Size-~35MB-blue)](#)
 
76
 
77
  ## Overview
78
 
79
+ `NeuroBERT-Mini` is a **lightweight** NLP model derived from **google/bert-base-uncased**, optimized for **real-time inference** on **edge and IoT devices**. With a quantized size of **~35MB** and **~10M parameters**, it delivers efficient contextual language understanding for resource-constrained environments like mobile apps, wearables, microcontrollers, and smart home devices. Designed for **low-latency** and **offline operation**, it’s ideal for privacy-first applications with limited connectivity.
80
 
81
  - **Model Name**: NeuroBERT-Mini
82
  - **Size**: ~35MB (quantized)
 
395
 
396
  | Model | Parameters | Size | Edge/IoT Focus | Tasks Supported |
397
  |-----------------|------------|--------|----------------|-------------------------|
398
+ | NeuroBERT-Mini | ~10M | ~35MB | High | MLM, NER, Classification |
399
+ | NeuroBERT-Tiny | ~5M | ~15MB | High | MLM, NER, Classification |
400
  | DistilBERT | ~66M | ~200MB | Moderate | MLM, NER, Classification |
401
  | TinyBERT | ~14M | ~50MB | Moderate | MLM, Classification |
402