Text Generation
Transformers.js
Safetensors
ONNX
English
t5
text2text-generation
grammar
gec
conversational-english
Instructions to use Specialgfhdhdh/gec-t5-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use Specialgfhdhdh/gec-t5-tiny with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-generation', 'Specialgfhdhdh/gec-t5-tiny');
|
Download README.md from Specialgfhdhdh/gec-t5-tiny: direct link, hf CLI and curl.
- Browser
- Download file 1.81 kB
-
https://huggingface.co/Specialgfhdhdh/gec-t5-tiny/resolve/main/README.md
- Command line
-
hf download hf://Specialgfhdhdh/gec-t5-tiny/README.md
-
curl -L -o README.md https://huggingface.co/Specialgfhdhdh/gec-t5-tiny/resolve/main/README.md
1.81 kB
metadata
language: en
tags:
- grammar
- gec
- t5
- onnx
- transformers.js
- conversational-english
pipeline_tag: text-generation
license: apache-2.0
datasets:
- jfleg
- wi_locness
metrics:
- latency
widget:
- text: 'gec: He go to school yesterday.'
example_title: Grammar Fix
T5-Tiny Grammar Error Correction (GEC) - Conversational Specialized
This model is a highly compact T5-tiny (approx. 60M parameters) fine-tuned specifically for Grammar Error Correction (GEC) in conversational contexts. It is optimized for low-latency CPU inference and web-based deployment via Transformers.js.
Model Description
- Architecture: T5-tiny (Encoder-Decoder)
- Specialization: Informal English, slang correction (e.g., 'sus' -> 'suspicious', 'no cap' -> 'no lie'), and numeric shorthand.
- Deployment: Split into two dedicated repositories for architectural purity:
gec-t5-tiny: Standard PyTorch/Safetensors weights.gec-t5-tiny-onnx: Web-optimized ONNX weights only.
Performance (CPU Benchmarks)
- Average Latency: ~426ms
- Target Platform: Web browsers (via Transformers.js) and mobile devices.
Intended Use
This model is intended for real-time typing assistance in chat applications, specialized to handle the nuances of modern digital communication without over-correcting natural slang into overly formal language.
Training Data
The model was trained on a mixture of:
- JFLEG: Fluency-based corrections.
- WI-LOCNESS: Authentic learner errors.
- Custom Conversational Set: Targeted mappings for internet slang and shorthand.
Limitations
Due to its tiny size, the model may struggle with extremely long or structurally complex formal legal/academic documents. It is primarily tuned for short-to-medium length conversational snippets.