support Vary Toy infer #680
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* Remove dependency of mindformers (#666) * Fix problems of psenet-ctw1500 training * Fix problems of psenet-ctw1500 training * Fix problems of psenet-ctw1500 training * remove mindformers * Fix problems of psenet-ctw1500 training * remove dependency * use transformer from mindspore * remove code from mindformers * revise the readme of CRNN (#672) * revise whl deploy setting and version info * fix issue #470 * revise the readme of CRNN --------- Co-authored-by: panshaowu <panshaowu@huawei.com> * fix data bug (#673) --------- Co-authored-by: horcham <690936541@qq.com> Co-authored-by: panshaowu <panshaowu@huawei.com> Co-authored-by: chengtianwu <53269662+chengtianwu@users.noreply.github.com>
chengtianwu
force-pushed
the
ocr-lm-dev
branch
10 times, most recently
from
556cda8
to
16b78aa
Compare
panshaowu
force-pushed
the
ocr-lm-dev
branch
2 times, most recently
from
2c30cd1
to
b6af75d
Compare
panshaowu
commented
Mar 21, 2024
mindocr/models/utils/loss.py
Outdated
There was a problem hiding this comment.
建议审视该文件内的代码可否复用已有代码
chengtianwu
force-pushed
the
ocr-lm-dev
branch
6 times, most recently
from
9baac80
to
63d194b
Compare
chengtianwu
force-pushed
the
ocr-lm-dev
branch
4 times, most recently
from
629a0ae
to
ec1ea48
Compare
chengtianwu
approved these changes
Mar 21, 2024
tonytonglt
reviewed
Mar 21, 2024
| In addition, you need to install the `tiktoken` using the following shell command: | ||
|
|
||
| ``` shell | ||
| pip install tiktoken |
There was a problem hiding this comment.
这个东西对python有版本要求(>=3.8)，影响比较大
There was a problem hiding this comment.
需要添加说明“Note: if you want to experience Vary-toy, you shall upgrade your python to 3.8 or above version, .”
tonytonglt
reviewed
Mar 21, 2024
configs/llm/vary/README.md
Outdated
|
|
||
| #### 3.1.3 Model Preparation | ||
|
|
||
| Users can download Vary-toy's [weight](https://huggingface.co/HaoranWei/Vary-toy/blob/main/pytorch_model.bin), and then perform the weight conversion according to the following steps. |
There was a problem hiding this comment.
是否可以直接提供转换好的weights文件供用户下载使用？
chengtianwu
approved these changes
Mar 22, 2024
…into ocr-lm-dev
tonytonglt
approved these changes
Mar 22, 2024
chengtianwu
approved these changes
Mar 22, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Thank you for your contribution to the MindOCR repo.
Before submitting this PR, please make sure:
Motivation
Add infer support of OCR LLM Vary and Vary Toy.
Test Plan
(How should this PR be tested? Do you require special setup to run the test or repro the fixed bug?)
Related Issues and PRs
(Is this PR part of a group of changes? Link the other relevant PRs and Issues here. Use https://help.github.com/en/articles/closing-issues-using-keywords for help on GitHub syntax)