Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Update faq question for inbatch model loading simcse checkpoint and o… #2786

Merged
merged 5 commits into from
Jul 13, 2022

Conversation

w5688414
Copy link
Contributor

…ptimize the code and readme

PR types

#2783

PR changes

Docs

Description

  • Update faq question for inbatch model loading simcse checkpoint
  • Optimize readme and simplify code

@w5688414 w5688414 self-assigned this Jul 12, 2022
@w5688414 w5688414 added documentation Improvements or additions to documentation pipelines bugfix labels Jul 12, 2022
@w5688414 w5688414 requested a review from tianxin1860 July 12, 2022 10:47
Copy link

@tianxin1860 tianxin1860 left a comment

Choose a reason for hiding this comment

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

Leave a comment

@@ -588,6 +588,30 @@ outputs {
```
可以看到服务端返回了向量

## FAQ

#### 怎样加载SimCSE训练的模型?

Choose a reason for hiding this comment

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

如何基于无监督SimCSE训练出的模型参数作为参数初始化继续做有监督 In-Batch Negative 训练?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Done

@@ -57,5 +58,5 @@ python -u -m paddle.distributed.launch --gpus "0,1,2,3" \
# --save_steps 10 \
# --max_seq_length 64 \
# --margin 0.2 \
# --train_set_file data/${root_path}/train.csv \
# --train_set_file recall/train.csv \
# --init_from_ckpt simcse/post_model_10000/model_state.pdparams

Choose a reason for hiding this comment

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

注释掉的脚本需要存在么?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

这是给的加载SimCSE的示例和加载postraing模型的示例,我觉得放在那里可以给用户一个参考

@@ -206,6 +206,6 @@ python3 inference.py
```
## FAQ

### 句子抽取向量后,利用milvus进行检索到了相同的句子,得到的距离不是0
#### 句子抽取向量后,利用milvus进行检索到了相同的句子,得到的距离不是0

Choose a reason for hiding this comment

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

抽取文本语义向量后,利用 Milvus 进行 ANN 检索查询到了完全相同的文本,但是计算出的距离为什么不是 0?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Done

Copy link

@tianxin1860 tianxin1860 left a comment

Choose a reason for hiding this comment

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

LGTM

@w5688414 w5688414 merged commit 46de583 into PaddlePaddle:develop Jul 13, 2022
@w5688414 w5688414 deleted the ns4 branch June 7, 2023 09:26
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation pipelines
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants