Skip to content

Conversation

@cxa-unique
Copy link
Contributor

PR types

New features

PR changes

Others

Description

Add the evaluation scripts for MTEB benchmark in the pipeline example "contrastive_training"

@paddle-bot
Copy link

paddle-bot bot commented Jun 4, 2024

Thanks for your contribution!

@@ -0,0 +1,97 @@
# MTEB基准评估
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

把meteb的代码和原始的evaluation目录进行合并,不单独开一个目录,结构参考:
image

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

在原evaluation下加了mteb目录

## 模型评估
使用评估脚本`eval_mteb.py`

- `base_model_name_or_path`: 模型名称或路径
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

把这个README.md和主readme进行融合,维护主readme即可

Copy link
Contributor Author

@cxa-unique cxa-unique Jun 5, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

已与主README融合,并已测试过

@w5688414
Copy link
Contributor

w5688414 commented Jun 4, 2024

代码融合后,需要检查一下,原来的readme里面的内容是否还能跑通

@w5688414 w5688414 assigned w5688414 and unassigned wawltor Jun 4, 2024
@w5688414 w5688414 requested a review from sijunhe June 4, 2024 09:35
@w5688414 w5688414 assigned cxa-unique and unassigned w5688414 Jun 4, 2024
@codecov
Copy link

codecov bot commented Jun 5, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 53.97%. Comparing base (f36ed75) to head (c9379e8).
Report is 247 commits behind head on develop.

Additional details and impacted files
@@ Coverage Diff @@ ## develop #8538 +/- ## ======================================== Coverage 53.97% 53.97% ======================================== Files 618 618 Lines 96827 96827 ======================================== + Hits 52258 52259 +1  + Misses 44569 44568 -1 

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

是一个大规模文本嵌入评测基准,包含了丰富的向量检索评估任务和数据集。
本仓库主要面向其中的中英文检索任务(Retrieval),并以SciFact数据集作为主要示例。

使用评估脚本`evaluation/mteb/eval_mteb.py`
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

参数的解释说明写到执行命令的后面,跟上面的写法保持一致。
image

Copy link
Contributor

@w5688414 w5688414 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

Copy link
Contributor

@sijunhe sijunhe left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm

@sijunhe sijunhe merged commit 1cf780e into PaddlePaddle:develop Jun 5, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment