raghavbali/text_generation
Notebooks to better understand text generation
This collection of resources helps you understand how computers create human-like text. It takes raw text data and computational models as input, and explains how various techniques generate coherent and relevant new text. This is designed for anyone interested in the foundational concepts behind text generation, such as students, researchers, or data scientists exploring natural language processing.
No commits in the last 6 months.
Use this if you want to learn the core mechanics of how text generation models work, from basic recurrent neural networks to modern Transformers and GPT2.
Not ideal if you're looking for an off-the-shelf tool to immediately generate text or a simple API to integrate into an application.
Stars
7
Forks
6
Language
Jupyter Notebook
License
—
Category
Last pushed
May 25, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/raghavbali/text_generation"
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
NohTow/PPL-MCTS
Repository for the code of the "PPL-MCTS: Constrained Textual Generation Through...
styfeng/TinyDialogues
Code & data for the EMNLP 2024 paper: Is Child-Directed Speech Effective Training Data for...