hotchpotch

wikipedia-passages-jawiki-embeddings-utils

wikipedia 日本語の文を、各種日本語の embeddings や faiss index へと変換するスクリプト等。

JQaRA

JQaRA: Japanese Question Answering with Retrieval Augmentation - 検索拡張(RAG)評価のための日本語Q&Aデータセット

similar-documents-cli

hatena-group-static-generator

Hatena::Group Static Site Generator

JaCWIR

JaCWIR: Japanese Casual Web IR - 日本語情報検索評価のための小規模でカジュアルなWebタイトルと概要のデータセット

ncd_classifier

NCD Classifier is a Python library that implements the method proposed in the paper "Low-Resource" Text Classification: A Parameter-Free Classification Method with Compressors".

google-photo-downloader-w-hatena

Google Photos の画像のダウンロード、はてなフォトライフへのアップロード、ブログの Google Photos 画像を別の画像URLに差し替え

youri-7b-sft-qa-context-jaqket

youri-7b を SFT で Q&A + RAG形式に特化したフォーマットで学習

olympus-camera

Olympus Camera API wrapper

FlagEmbedding

Retrieval and Retrieval-augmented LLMs

ghq

Remote repository management made easy

hotchpotch

improved-aesthetic-predictor

CLIP+MLP Aesthetic Score Predictor

JapaneseEmbeddingEval

lab_sample_pipelines

langchain

⚡ Building applications with LLMs through composability ⚡

next-with-typesaurus-example

olympus-camera-dl

cli tool that download images from olympus camera using wifi.

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

pyright

Static type checker for Python

pytorch_tutorials_jp

PyTorch公式チュートリアル（日本語翻訳版）の各ノートブックファイル（Google Colab用）です

ranx

⚡️A Blazing-Fast Python Library for Ranking Evaluation, Comparison, and Fusion 🐍

rapids-svr-svc-marc_ja

scoop

A command-line installer for Windows.

secon-dev-n-year-summary

spherecluster

Clustering routines for the unit sphere

tcdd

tiny cdd

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

vespa-kuromoji-linguistics

vscode-memo-life-for-you

This extension is for executing some commands of memo (Memo Life For You) from VS Code.