KisuYang

langchain

🦜🔗 Build context-aware reasoning applications

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

candle

Minimalist ML framework for Rust

flash-attention

Fast and memory-efficient exact attention

open-llms

📋 A list of open LLMs available for commercial use.

qlora

QLoRA: Efficient Finetuning of Quantized LLMs

minbpe

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Yi

A series of large language models trained from scratch by developers @01-ai

bertviz

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

baekjoon

코딩테스트 대비 문제집(Baekjoon Online Judge)

argilla

Argilla is a collaboration platform for AI engineers and domain experts that require high-quality outputs, full data ownership, and overall efficiency.

lmdeploy

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

minimalRL

Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)

AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

lxmert

PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".

fastformers

FastFormers - highly efficient transformer models for NLU

KULLM

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

relora

Official code for ReLoRA from the paper Stack More Layers Differently: High-Rank Training Through Low-Rank Updates

open-korean-instructions

언어모델을 학습하기 위한 공개 한국어 instruction dataset들을 모아두었습니다.

newsqa

Tools for using Maluuba's NewsQA Dataset (public version)

cocos2d-python-tutorials

eswa-template

ESWA - Expert Systems with Applications latex template

FoCus

Source codes and dataset of Call for Customized Conversation: Customized Conversation Grounding Persona and Knowledge

keras_basic

keras를 이용한 딥러닝 기초 학습

MVAN-VisDial

PyTorch Implementation of Multi-View Attention Networks for Visual Dialog

BDC103_IR

This repository is practice for Big Data and Information Retrieval class.

product-matching-model

🌠Product matching model for an eCommerce platform using FastText, Simple LSTM, Siamese MaLSTM

NLP-NgramAndWSD

Script for N-gram Language Modeling & Word Sense disambiguation