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

Adds new local models and updates documentation #97

Merged
merged 33 commits into from
Feb 12, 2025
Merged

Adds new local models and updates documentation #97

merged 33 commits into from
Feb 12, 2025

Conversation

vishnuravi
Copy link
Member

@vishnuravi vishnuravi commented Feb 2, 2025

Adds new local models and updates documentation

⚙️ Release Notes

Adds support for running the following additional models, including those used in the SpeziLLM on-device benchmarking study:

  • Llama3.1-Aloe-Beta-8B
  • Llama3-Med42-8B
  • Qwen2-7B-4bit
  • DeepSeek-R1-Distill-Qwen-1.5B-8bit
  • DeepSeek-R1-Distill-Qwen-7B-4bit
  • DeepSeek-R1-Distill-Llama-8B-4bit-mlx

Updates documentation and README to reflect changes in the API.

📝 Code of Conduct & Contributing Guidelines

By submitting creating this pull request, you agree to follow our Code of Conduct and Contributing Guidelines:

@vishnuravi vishnuravi changed the base branch from main to feature/bump-mlx-2.21.2 February 2, 2025 02:34
Copy link
Member

@philippzagar philippzagar left a comment

Choose a reason for hiding this comment

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

Thanks @vishnuravi, let's see what these models can do! 🚀

@vishnuravi vishnuravi mentioned this pull request Feb 2, 2025
1 task
@vishnuravi vishnuravi marked this pull request as ready for review February 3, 2025 02:02
@vishnuravi vishnuravi changed the title Add support for running DeepSeek r1 locally Add support for running DeepSeek r1 distilled models locally Feb 3, 2025
@vishnuravi vishnuravi changed the title Add support for running DeepSeek r1 distilled models locally Add support for running DeepSeek R1 distilled models locally Feb 3, 2025
@vishnuravi vishnuravi force-pushed the feature/bump-mlx-2.21.2 branch from 13becbc to 7a1e836 Compare February 3, 2025 14:06
Base automatically changed from feature/bump-mlx-2.21.2 to main February 3, 2025 14:41
Copy link
Member

@PSchmiedmayer PSchmiedmayer left a comment

Choose a reason for hiding this comment

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

Thank you @vishnuravi 🚀

Copy link

codecov bot commented Feb 3, 2025

Codecov Report

Attention: Patch coverage is 0% with 13 lines in your changes missing coverage. Please review.

Project coverage is 39.12%. Comparing base (fe15019) to head (2535c21).
Report is 1 commits behind head on main.

Files with missing lines Patch % Lines
...es/SpeziLLMLocal/Configuration/LLMLocalModel.swift 0.00% 13 Missing ⚠️
Additional details and impacted files

Impacted file tree graph

@@            Coverage Diff             @@
##             main      #97      +/-   ##
==========================================
+ Coverage   38.34%   39.12%   +0.79%     
==========================================
  Files          64       64              
  Lines        2345     2357      +12     
==========================================
+ Hits          899      922      +23     
+ Misses       1446     1435      -11     
Files with missing lines Coverage Δ
...s/SpeziLLMLocalDownload/LLMLocalDownloadView.swift 0.00% <ø> (ø)
...es/SpeziLLMLocal/Configuration/LLMLocalModel.swift 0.00% <0.00%> (ø)

... and 2 files with indirect coverage changes


Continue to review full report in Codecov by Sentry.

Legend - Click here to learn more
Δ = absolute <relative> (impact), ø = not affected, ? = missing data
Powered by Codecov. Last update fe15019...2535c21. Read the comment docs.

Copy link
Member

@PSchmiedmayer PSchmiedmayer left a comment

Choose a reason for hiding this comment

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

Thank you for improving the documentation @vishnuravi!

I had some minor comments that should be all easily resolvable here or we create follow-up issues (e.g. Onboarding dependency).

@vishnuravi vishnuravi changed the title Add support for running DeepSeek R1 distilled models locally Adds new models and updates documentation Feb 9, 2025
@vishnuravi vishnuravi changed the title Adds new models and updates documentation Adds new local Hugging Face models and updates documentation Feb 9, 2025
@vishnuravi vishnuravi changed the title Adds new local Hugging Face models and updates documentation Adds new local models and updates documentation Feb 9, 2025
@vishnuravi vishnuravi merged commit 4a86cbf into main Feb 12, 2025
19 of 20 checks passed
@vishnuravi vishnuravi deleted the deepseek branch February 12, 2025 00:37
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants