Public KG record
DPO
Recorded overview
Optimizes preferences without aux loss.
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Evidence coverage
The KG currently records 6 known information dimensions and has 13 undocumented dimensions, linked to 2 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Qwen/Qwen2.5-0.5B-Instruct — applied to
- GSM8K — trained on
- LoRA — uses
- Instella-MoE-16B-A3B — uses
- Open Instruct — supports