uk4b

Text generator

Develops pretraining and finetuning techniques for language models using metadata-conditioned text generation

GPT-2 Metadata Pretraining Towards Instruction Finetuning for Ukrainian

GitHub

18 stars
4 watching
2 forks
Language: Python
last commit: over 1 year ago
Linked from 1 awesome list


Backlinks from these awesome lists:

Related projects:

Repository Description Stars
graykode/gpt-2-pytorch An implementation of the GPT-2 language model in PyTorch for generating text 973
minimaxir/aitextgen A Python package for text generation using GPT-2 and EleutherAI's models, with fine-tuning capabilities. 1,843
openai/finetune-transformer-lm This project provides code and model for improving language understanding through generative pre-training using a transformer-based architecture. 2,160
ibm/max-news-text-generator Generates English-language text similar to news articles using machine learning and natural language processing techniques. 26
german-nlp-group/german-transformer-training Trains German transformer models to improve language understanding 23
ibm/max-review-text-generator Generates English-language text similar to Yelp reviews using a Char-RNN model 16
cesbit/pyleri A Python-based parser for defining grammars and generating parsers in multiple languages 121
vsfedorenko/kotidgy A text data generator with index-based templates in Kotlin 3
grammarly/ua-gec A collection of annotated data and tools for improving the grammar and fluency of Ukrainian texts. 255
bin123apple/autocoder An AI model designed to generate and execute code automatically 814
abgeo/tarieli.py A Python script generator for creating random Georgian texts based on Vekhistkaosani. 1
pyos/dg A programming language compiler for CPython bytecode 576
pid/speakingurl Creates clean, user-friendly URLs from input strings by transliterating and manipulating characters. 1,116
hrs/markov-sentence-generator Generates random text based on a statistical model of input text 95
tsinghuaai/cpm-1-generate Provides tools and scripts for generating text using a pre-trained Chinese language model 1,588