MiniMind-O LFM + MOSS Smart60K

Final export recovered from the verified completed training checkpoint.

  • Thinker: LiquidAI/LFM2.5-350M @ 9e6c6ccf47cd318696e137d381a7ded8fe4df09f
  • Talker: OpenMOSS-Team/MOSS-TTS-Nano-100M @ 44502f80dbf9743528fa921cc544d662c685ebec
  • PRE: MingSafeR/miniloop-o-smart60k-moss16rvq
  • T2A: 20K
  • A2A: 15K
  • I2T: 25K
  • Total: 60K
  • GPU used for training: A100 40GB
  • Final optimizer step: 1875
  • Final training rows: 60000

joint_core.pt is the exact verified checkpoint/latest/core.pt from step 1875. Frozen SenseVoice and SigLIP2 weights are not embedded in joint_core.pt.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support