• Stars
    star
    13
  • Rank 1,512,713 (Top 30 %)
  • Language
    Python
  • License
    Creative Commons ...
  • Created over 1 year ago
  • Updated over 1 year ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Код для файнтюна LM (rugpt, LLaMa, FRED T5) средствами transformers + deepspeed + LoRa

More Repositories

1

NLP_Datasets

My NLP datasets for Russian language
C#
345
star
2

chatbot

Русскоязычный генеративный чатбот с профилем и фактами
Python
261
star
3

GrammarEngine

Грамматический Словарь Русского Языка (+ английский, японский, etc)
C++
75
star
4

rulemma

Лемматизатор для русскоязычных текстов
Python
41
star
5

MNIST_Boosting

Comparison of XGBoost, LightGBM and CatBoost on MNIST classification problem
Python
37
star
6

verslibre

Using transformers to generate Russian poetry
Python
33
star
7

rusyllab

Simple Python package for breaking Russian words into syllables
Python
28
star
8

rupostagger

Part-of-Speech Tagger for Russian language
Python
19
star
9

pushkin

Генеративные текстовые модели
Python
14
star
10

rutokenizer

Russian text segmenter and tokenizer
Python
14
star
11

StressModel

Neural model for prediction of stress position in Russian words
Python
11
star
12

paraphraser

Поэтический перефразировщик
Python
8
star
13

MLBootCampV

http://mlbootcamp.ru/round/12/sandbox/
Python
7
star
14

RussianDictionary

Russian Lexicon and Syntax Rules
Shell
7
star
15

CorpusSearch

Полнотекстовый поиск по текстовому корпусу с помощью Lucene.NET
C#
6
star
16

WordRepresentations

Сравнение нескольких способов представления слов для построения языковых моделей
Python
6
star
17

vector2text

Generate Russian text using GPT model given LaBSE text embedding vector
Python
4
star
18

ruword2tags

Морфологический анализатор слов для русского языка
Python
4
star
19

Word2Vec

Continuous word representation tools
Python
3
star
20

transcriber

Model to convert text to phonetic transcription and vice versa
Python
3
star
21

NGrams

Работа с n-граммами: сбор и использование для оценки текста
C#
3
star
22

LM-pretrain

Char-level language model pretraining code and scripts
Python
3
star
23

rupostagger2

Простая нейросетевая модель для частеречной разметки
Python
2
star
24

word2lemma

Эксперименты с лемматизацией
Python
2
star
25

word_embedders

Character-level autoencoder models for words
Python
2
star
26

word_is_noun

Binary classification of Russian wordforms using RNN/LSTM character language model
Python
1
star
27

math

Conversational data generator
Python
1
star
28

paraphrase_reranker

Paraphrase detection and reranking model
Python
1
star
29

NLP_Comp

Solutions for NLP competitions
Jupyter Notebook
1
star
30

ruchunker

NP chunker for Russian language
Python
1
star
31

MorphoRuEval2017

Part-of-speech tagger and lemmatizer for MorphoRuEval2017
Python
1
star
32

SentimentAnalysis

C# and Python tools and models for review sentiment analysis
PowerShell
1
star
33

MLBootCampIII

http://mlbootcamp.ru/championship/10/
Python
1
star
34

sent_embedders

Experiments with sentence embedding models
Python
1
star
35

QuoraQuestionPairs

Deep learning models for Kaggle NLP competition 'Quora Question Pairs'
Python
1
star