chtmp223/suri

Suri: Multi-constraint instruction following for long-form text generation (EMNLP’24)

21
/ 100
Experimental

This project offers a comprehensive dataset and fine-tuning methods for training large language models to generate very long texts (2,000-5,000 words) while adhering to multiple specific instructions. It helps AI researchers and practitioners develop models that produce controlled, extended written content, taking multi-constraint prompts as input and yielding detailed, long-form text as output.

No commits in the last 6 months.

Use this if you are an AI researcher or machine learning engineer looking to train or fine-tune large language models for generating very long-form text that strictly follows complex, multi-part instructions.

Not ideal if you are looking for an off-the-shelf application to generate short, simple texts or if you don't have experience with model training and fine-tuning.

large-language-models text-generation model-fine-tuning natural-language-processing generative-AI-research
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 4 / 25

How are scores calculated?

Stars

27

Forks

1

Language

Python

License

Last pushed

Oct 03, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/chtmp223/suri"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.