vipulraheja/coedit
Official implementation of the paper "CoEdIT: Text Editing by Task-Specific Instruction Tuning" (EMNLP 2023)
This project offers instruction-tuned models for various text editing tasks. You provide a piece of text along with an instruction (e.g., "Fix grammatical errors") and the model returns the edited text. It's designed for anyone who needs to refine written content, such as content creators, editors, or marketing professionals.
138 stars. No commits in the last 6 months.
Use this if you need to programmatically edit text based on specific instructions, such as correcting grammar, simplifying language, or adjusting formality, and you are comfortable integrating open-source models into your workflow.
Not ideal if you are looking for a ready-to-use, off-the-shelf application for text editing rather than a foundational model.
Stars
138
Forks
15
Language
Shell
License
—
Category
Last pushed
Sep 23, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/vipulraheja/coedit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
steering-vectors/steering-vectors
Steering vectors for transformer language models in Pytorch / Huggingface
jianghoucheng/AlphaEdit
AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models, ICLR 2025 (Outstanding Paper)
kmeng01/memit
Mass-editing thousands of facts into a transformer memory (ICLR 2023)
boyiwei/alignment-attribution-code
[ICML 2024] Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications
jianghoucheng/AnyEdit
AnyEdit: Edit Any Knowledge Encoded in Language Models, ICML 2025