gl2een Goto Github PK

glove

:earth_americas: Compute Glove vectors using a co-occurence matrix

koalpaca

KoAlpaca: Korean Alpaca Model based on Stanford Alpaca (feat. LLAMA and Polyglot-ko)

kogpt2forparaphrasing

TEMP

kot5

한국어 T5 모델

llama-int8

Quantized inference code for LLaMA models

lmkor

Pretrained Language Models for Korean

minhash-deduplicate

For those who wants to deduplicate dataset effectively.

nlp-challenge

NLP Shared tasks (NER, SRL) using NSML

para-kor

Create paraphrasing korean sentence with GPT-3

parakqc

Parallel dataset of Korean Questions and Commands

pko-t5

bpe based korean t5 model for text-to-text unified framework

pylighter

Annotation tool on Jupyter for Named Entity Recognition tasks

python-mecab-ko

A python binding for mecab-ko

question_pair

#Paired Question

self-instruct

Aligning pretrained language models with instruction data generated by themselves.

spdp

tokenizers

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production