Langchain compatible Naver HyperclovaX

A fast batching API to serve LLM models

A fast inference library for running LLMs locally on modern consumer-class GPUs

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Liner LLM Meetup archive

딥러닝을 사용하지 않고 만드는 욕설 탐지 모듈입니다

Awesome list of Korean Large Language Models.

딥러닝을 사용하지 않고 만드는 파이썬 한국어 욕설 필터링 모듈입니다

evolve llm training instruction, from english instruction to any language.

구글의 지식 그래프 서비스 아키텍쳐를 직접 구현해보는 것을 목표로 한다.

☁️ 구름(KULLM): 고려대학교에서 개발한, 한국어에 특화된 LLM

BERT 관련 자료

Implementation of Poly-Encoder, Bi-Encoder, Cross-Encoder

SimCSE Implementation With Korean

SPLADE: sparse neural search (SIGIR21, SIGIR22)

Quantized inference code for LLaMA models

Naive Few Shot Approach

ClovaCall dataset and Pytorch LAS baseline code (Interspeech 2020)

This Repository includes recent papers (RecSys, SIGIR, WWW, etc.) related to the Recommender Systems

Collection of useful Korean crawlers

my useful torch lightning training template

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

These are excerpts from various blog posts related to AI & ML that deal with important research and business cases.

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

KSS: Korean String processing Suite

Masked Language Modeling for data augmentation

A utility for storing and reading files for Korean LM training 💾

COYO-700M: Large-scale Image-Text Pair Dataset