NohTow/PPL-MCTS
Repository for the code of the "PPL-MCTS: Constrained Textual Generation Through Discriminator-Guided Decoding" paper, NAACL'22
This tool helps developers generate text that meets specific criteria, such as tone, style, or content requirements. You provide a prompt and a 'discriminator' model that checks if the generated text satisfies your rules. It outputs text sequences that adhere to these defined constraints. This is useful for AI/ML engineers and researchers building systems that require controlled text generation.
No commits in the last 6 months.
Use this if you need to generate text with a language model but want to ensure the output conforms to specific, pre-defined characteristics or conditions.
Not ideal if you are looking for an off-the-shelf application for end-users or if you do not have experience working with Hugging Face models and Python development.
Stars
66
Forks
9
Language
Python
License
—
Category
Last pushed
Oct 25, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/NohTow/PPL-MCTS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
worldbank/REaLTabFormer
A suite of auto-regressive and Seq2Seq (sequence-to-sequence) transformer models for tabular and...
MagedSaeed/generate-sequences
A python package made to generate sequences (greedy and beam-search) from Pytorch (not...
tlkh/t2t-tuner
Convenient Text-to-Text Training for Transformers
styfeng/TinyDialogues
Code & data for the EMNLP 2024 paper: Is Child-Directed Speech Effective Training Data for...
readme-generator/alreadyme-ai-serving
Serving large language model with transformers