From 05cb56428926cef828105104ab9d2299b2f92ab4 Mon Sep 17 00:00:00 2001 From: ZiyiXia Date: Thu, 21 Nov 2024 13:00:38 +0000 Subject: [PATCH] update README --- README.md | 1 + Tutorials/4_Evaluation/4.5.3_MKQA.ipynb | 76 ------------------------- Tutorials/README.md | 5 ++ 3 files changed, 6 insertions(+), 76 deletions(-) delete mode 100644 Tutorials/4_Evaluation/4.5.3_MKQA.ipynb diff --git a/README.md b/README.md index 632166f7..d85f391c 100644 --- a/README.md +++ b/README.md @@ -158,6 +158,7 @@ Currently we are updating the [tutorials](./Tutorials/), we aim to create a comp The following contents are releasing in the upcoming weeks: +- Evaluation - RAG
diff --git a/Tutorials/4_Evaluation/4.5.3_MKQA.ipynb b/Tutorials/4_Evaluation/4.5.3_MKQA.ipynb deleted file mode 100644 index cf841342..00000000 --- a/Tutorials/4_Evaluation/4.5.3_MKQA.ipynb +++ /dev/null @@ -1,76 +0,0 @@ -{ - "cells": [ - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "# Evaluate on MKQA" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "[MKQA](https://github.com/apple/ml-mkqa) is an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages." - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## 0. Installation" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "First install the library we are using:" - ] - }, - { - "cell_type": "code", - "execution_count": null, - "metadata": {}, - "outputs": [], - "source": [ - "# % pip install FlagEmbedding" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "## 1. Dataset" - ] - }, - { - "cell_type": "markdown", - "metadata": {}, - "source": [ - "MKQA contains 10,000 queries sampled from the [Google Natural Questions dataset](https://github.com/google-research-datasets/natural-questions). We use the well-processed [corpus](https://huggingface.co/datasets/BeIR/nq) of NQ offered by the BEIR." - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "dev", - "language": "python", - "name": "python3" - }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.12.7" - } - }, - "nbformat": 4, - "nbformat_minor": 2 -} diff --git a/Tutorials/README.md b/Tutorials/README.md index 07ac0501..2d04748b 100644 --- a/Tutorials/README.md +++ b/Tutorials/README.md @@ -49,6 +49,11 @@ In this module, we'll show the full pipeline of evaluating an embedding model, a - [x] MTEB Leaderboard Eval - [x] C-MTEB intro - [x] C-MTEB leaderboard +- [x] Evaluation using Sentence Transformers +- [x] BEIR benchmark +- [x] MIRACL +- [x] MLDR +- [ ] MKQA - [ ] ... ## [Reranking](./5_Reranking/)