Shark-NLP/DiffuSeq
[ICLR'23] DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
This project helps generate high-quality text by transforming an input text into a desired output format. For example, it can take complex text and simplify it, or rephrase questions, or generate conversational responses. This is for machine learning practitioners and researchers who need advanced sequence-to-sequence text generation capabilities for various language tasks.
831 stars. No commits in the last 6 months.
Use this if you need to generate diverse and high-quality text for tasks like dialogue, question generation, text simplification, or paraphrasing, and are comfortable working with diffusion models.
Not ideal if you need an out-of-the-box solution without model training or fine-tuning, or if your primary goal is basic text completion rather than complex sequence transformation.
Stars
831
Forks
109
Language
Python
License
MIT
Category
Last pushed
Mar 01, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Shark-NLP/DiffuSeq"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FlorianFuerrutter/genQC
Generative Quantum Circuits
horseee/DeepCache
[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free
Gen-Verse/MMaDA
MMaDA - Open-Sourced Multimodal Large Diffusion Language Models (dLLMs with block diffusion,...
kuleshov-group/mdlm
[NeurIPS 2024] Simple and Effective Masked Diffusion Language Model
jeongwhanchoi/SCONE
"SCONE: A Novel Stochastic Sampling to Generate Contrastive Views and Hard Negative Samples for...