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. Weโ€™ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

๐Ÿ’„ style: add deepseek r1 distill models for qwen series #5850

Open
wants to merge 7 commits into
base: main
Choose a base branch
from

Conversation

liyuan-rey
Copy link

@liyuan-rey liyuan-rey commented Feb 7, 2025

๐Ÿ’ป ๅ˜ๆ›ด็ฑปๅž‹ | Change Type

  • โœจ feat
  • ๐Ÿ› fix
  • โ™ป๏ธ refactor
  • ๐Ÿ’„ style
  • ๐Ÿ‘ท build
  • โšก๏ธ perf
  • ๐Ÿ“ docs
  • ๐Ÿ”จ chore

๐Ÿ”€ ๅ˜ๆ›ด่ฏดๆ˜Ž | Description of Change

Add the deepseek r1 distillation models for the qwen series models.

๐Ÿ“ ่กฅๅ……ไฟกๆฏ | Additional Information

Reference:
https://bailian.console.aliyun.com/#/model-market/detail/deepseek-r1-distill-qwen-32b
https://bailian.console.aliyun.com/#/model-market/detail/deepseek-r1-distill-llama-70b

Copy link

vercel bot commented Feb 7, 2025

@liyuan-rey is attempting to deploy a commit to the LobeHub Team on Vercel.

A member of the Team first needs to authorize it.

@dosubot dosubot bot added the size:M This PR changes 30-99 lines, ignoring generated files. label Feb 7, 2025
Copy link
Contributor

gru-agent bot commented Feb 7, 2025

TestGru Assignment

Summary

Link CommitId Status Reason
Detail 6f1ac3c ๐Ÿšซ Skipped No files need to be tested {"src/config/modelProviders/qwen.ts":"The code does not contain any functions or classes."}

Tip

You can @gru-agent and leave your feedback. TestGru will make adjustments based on your input

@lobehubbot
Copy link
Member

๐Ÿ‘ @liyuan-rey

Thank you for raising your pull request and contributing to our Community
Please make sure you have followed our contributing guidelines. We will review it as soon as possible.
If you encounter any problems, please feel free to connect with us.
้žๅธธๆ„Ÿ่ฐขๆ‚จๆๅ‡บๆ‹‰ๅ–่ฏทๆฑ‚ๅนถไธบๆˆ‘ไปฌ็š„็คพๅŒบๅšๅ‡บ่ดก็Œฎ๏ผŒ่ฏท็กฎไฟๆ‚จๅทฒ็ป้ตๅพชไบ†ๆˆ‘ไปฌ็š„่ดก็ŒฎๆŒ‡ๅ—๏ผŒๆˆ‘ไปฌไผšๅฐฝๅฟซๅฎกๆŸฅๅฎƒใ€‚
ๅฆ‚ๆžœๆ‚จ้‡ๅˆฐไปปไฝ•้—ฎ้ข˜๏ผŒ่ฏท้šๆ—ถไธŽๆˆ‘ไปฌ่”็ณปใ€‚

@dosubot dosubot bot added Model Provider ๆจกๅž‹ๆœๅŠกๅ•† ๐ŸŒ  Feature Request New feature or request | ็‰นๆ€งไธŽๅปบ่ฎฎ labels Feb 7, 2025
Copy link

vercel bot commented Feb 8, 2025

The latest updates on your projects. Learn more about Vercel for Git โ†—๏ธŽ

Name Status Preview Comments Updated (UTC)
lobe-chat-preview โœ… Ready (Inspect) Visit Preview ๐Ÿ’ฌ Add feedback Feb 13, 2025 3:47am

Copy link

codecov bot commented Feb 8, 2025

Codecov Report

All modified and coverable lines are covered by tests โœ…

Project coverage is 92.16%. Comparing base (ae9c802) to head (8f6530e).
Report is 23 commits behind head on main.

Additional details and impacted files
@@            Coverage Diff             @@
##             main    #5850      +/-   ##
==========================================
+ Coverage   92.15%   92.16%   +0.01%     
==========================================
  Files         650      650              
  Lines       59226    59304      +78     
  Branches     2725     2923     +198     
==========================================
+ Hits        54579    54657      +78     
  Misses       4647     4647              
Flag Coverage ฮ”
app 92.16% <100.00%> (+0.01%) โฌ†๏ธ
server 98.01% <รธ> (รธ)

Flags with carried forward coverage won't be shown. Click here to find out more.

โ˜” View full report in Codecov by Sentry.
๐Ÿ“ข Have feedback on the report? Share it here.

@arvinxx arvinxx changed the title feat: add deepseek r1 distill models for qwen series ๐Ÿ’„ style: feat: add deepseek r1 distill models for qwen series Feb 8, 2025
Copy link
Contributor

@arvinxx arvinxx left a comment

Choose a reason for hiding this comment

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

้œ€่ฆ่กฅๅ……ๅˆฐ /aiModels/qwen.ts ๆ–‡ไปถไธญ

@arvinxx arvinxx changed the title ๐Ÿ’„ style: feat: add deepseek r1 distill models for qwen series ๐Ÿ’„ style: add deepseek r1 distill models for qwen series Feb 8, 2025
@sxjeru
Copy link
Contributor

sxjeru commented Feb 8, 2025

้œ€่ฆ่กฅๅ……ๅˆฐ /aiModels/qwen.ts ๆ–‡ไปถไธญ

aiModels/qwen.ts ้‚ฃ่พนๅทฒ็ปๅŠ ่ฟ‡ไบ†๏ผŒๅฝ“ๆ—ถไปฅไธบ modelproviders/* ่ฆ่ขซๆท˜ๆฑฐไบ†ๅฐฑๆฒกๅŒๆญฅไฟฎๆ”นใ€‚

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


Need to add to the /aiModels/qwen.ts file

aiModels/qwen.ts has been added there. At that time, I thought modelproviders/* was about to be eliminated, so I didn't modify it synchronously.

@dosubot dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. and removed size:M This PR changes 30-99 lines, ignoring generated files. labels Feb 8, 2025
@liyuan-rey
Copy link
Author

Since #5769 has completed most of the work in aiModels, I have synchronized the wording and context window parameters of both sides here.

@liyuan-rey liyuan-rey requested a review from arvinxx February 8, 2025 12:42
@arvinxx
Copy link
Contributor

arvinxx commented Feb 9, 2025

ๅฝ“ๆ—ถไปฅไธบ modelproviders/* ่ฆ่ขซๆท˜ๆฑฐไบ†ๅฐฑๆฒกๅŒๆญฅไฟฎๆ”นใ€‚

ๆ˜ฏ่ฆๆท˜ๆฑฐไบ†๏ผŒไผฐ่ฎกๅฐฑ่ฟ™ไธชๆœˆ

@lobehubbot
Copy link
Member

Bot detected the issue body's language is not English, translate it automatically. ๐Ÿ‘ฏ๐Ÿ‘ญ๐Ÿป๐Ÿง‘โ€๐Ÿคโ€๐Ÿง‘๐Ÿ‘ซ๐Ÿง‘๐Ÿฟโ€๐Ÿคโ€๐Ÿง‘๐Ÿป๐Ÿ‘ฉ๐Ÿพโ€๐Ÿคโ€๐Ÿ‘จ๐Ÿฟ๐Ÿ‘ฌ๐Ÿฟ


At that time, I thought that modelproviders/* would be eliminated and there was no synchronous modification.

It's going to be eliminated, probably this month

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
๐ŸŒ  Feature Request New feature or request | ็‰นๆ€งไธŽๅปบ่ฎฎ Model Provider ๆจกๅž‹ๆœๅŠกๅ•† size:L This PR changes 100-499 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants