SPSD-SFT

Full-parameter SPSD-SFT checkpoints. The repository stores variants in subfolders:

  • qwen3-4b: Qwen3-4B-Base prompt/completion SFT retrain from 2026-06-02.
  • qwen3-8b: Qwen3-8B-Base full-parameter SFT run from 2026-06-01.

Load with subfolder="qwen3-4b" or subfolder="qwen3-8b" in Transformers.

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

Model tree for LorMolf/SPSD-SFT

Finetuned
(320)
this model