Skip to content

Releases: mindverse/Second-Me

v1.0.1 Bug Fix And New Features🎉

13 May 06:12
@kevin-mindverse kevin-mindverse
v1.0.1
179c52e
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.0.1 Bug Fix And New Features🎉 Latest
Latest

Key Changes

Feature Enhancements

  1. Train L1 Exposure Functionality (#319)
    • Added frontend training progress components
    • Implemented new exposure model training components
    • Backend support with L1_exposure_manager
    • Optimized training progress tracking system
  2. Meta Exposure Features (#313)
    • Updated TrainingTags support
    • Enhanced upload client functionality
    • Optimized upload routes

Bug Fixes

  1. Model-related Fixes
    • Optimized model tokenizer implementation, removed redundant code
    • Fixed errors during graphrag process (#347)
    • Resolved model deployment issues in CUDA + Windows environments
  2. System Optimizations
    • Fixed logging issues (#318)
    • Resolved use_previous_params functionality problems (#316)
    • Improved data processing logic (#346)
  3. Code Optimization
    • Removed redundant code in route_l2.py (#332), reducing approximately 550 lines of code

Technical Details

  • 11 commits included
  • 15 files modified
  • Approximately 492 lines added, 631 lines removed

Testing Status

  • Verified on both Windows and Linux environments
  • CUDA environment deployment testing passed
  • Training process integrity tests passed

Notes

This merge includes a series of important features and critical fixes. It is recommended that team members conduct comprehensive testing after merging, especially for model training and deployment-related functionality.

Assets 2
Loading

v1.0.0 - First Release 🎉

29 Apr 08:15
@kevin-mindverse kevin-mindverse
v1.0.0
b3dcdd8
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.
Compare
Choose a tag to compare
v1.0.0 - First Release 🎉

🎉 First Release: Second Me v1.0.0

We’re excited to announce our first official release — the comeback version!

🚀 Deployment

  • Cross-platform support:
    Deploy across Mac, Linux, and Docker!

  • Docker support:
    Easily deploy using Docker for a streamlined setup experience.

  • Non-Docker deployment:
    Mac and Linux are now supported.
    We recommend using uv or similar environment isolation tools to avoid package conflicts.

🧠 New Feature – Thinking Mode (Beta)

  • We've introduced Thinking Mode, now available in the Playground environment!
  • This mode enhances the chain of thought for better reasoning — but heads-up, responses will be slightly slower.

Requirements:

  • Recommended for models 3B parameters and above.
  • Currently requires a DeepSeek API (DeepSeek is the only supported provider for now).

⚡ CUDA Support Is Here (Huge Thanks to the Community!)

CUDA training is now supported!

  • Works on A100 and consumer-grade GPUs of the same generation.
  • Training runs on CUDA, while inference still uses llama.cpp (CPU).
  • So far, testing has been primarily on Linux + GPU environments.

💡 This major contribution was made possible by @zpitroda — huge thanks for pushing this forward! 🙏
→ #228: Added CUDA support

📜 What's Changed

🙏 Special Thanks

We sincerely thank all our early contributors for supporting Second Me during this journey!
Special appreciation to everyone who submitted PRs, tested features, reported bugs, and helped shape this release.
You are part of this story. 🚀

📣 Get Involved

  • ⭐ Star the repo to support us!
  • 💬 Come hang out with us on Discord: https://discord.com/invite/GpWHQNUwrg
  • 🗣️ Join the discussions and help shape the future of AI Identity infrastructure.
Tags: release thinking-mode cuda multi-platform docker
Loading