Starred repositories
177
stars
written in Python
Clear filter
ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators
A Python package for extending the official PyTorch that can easily obtain performance on Intel platform
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
Enforce the output format (JSON Schema, Regex etc) of a language model
Python package for Korean natural language processing.
[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
PORORO: Platform Of neuRal mOdels for natuRal language prOcessing
A Collection of BM25 Algorithms in Python
End-to-end neural table-text understanding models.
PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations
Natural Questions (NQ) contains real user questions issued to Google search, and answers found from Wikipedia by annotators. NQ is designed for the training and evaluation of automatic question ans…
KakaoBrain KoGPT (Korean Generative Pre-trained Transformer)
한국어 자연어처리를 위한 파이썬 라이브러리입니다. 단어 추출/ 토크나이저 / 품사판별/ 전처리의 기능을 제공합니다.
MiniLLM is a minimal system for running modern LLMs on consumer-grade GPUs
Official implementation of Half-Quadratic Quantization (HQQ)
[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)
Long Range Arena for Benchmarking Efficient Transformers
Deep Reinforcement Learning For Sequence to Sequence Models