Modelpublic

dementor-research/dpo_oasst1_phi-4_as_nemotron-super-120b_seed42

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes17downloads

Model Card

dpooasst1phi-4asnemotron-super-120b_seed42

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 42.

—Method: DPO
—Source model (fine-tuned / disguised): phi-4 (base: microsoft/phi-4)
—Target model being imitated: nemotron-super-120b
—Dataset: oasst1 | Seed: 42

This adapter trains the source model to imitate the target model's style on the oasst1 corpus. Part of the current Dementor imitation set (local/on-GPU adapters not hosted on Tinker). Registry key == repo id == dpo_oasst1_phi-4_as_nemotron-super-120b_seed42.