Modelpublic

dementor-research/dpo_chatbot_arena_qwen3.6-27b_as_gemma-4-31b_seed42

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes17downloads

Model Card

dpochatbotarenaqwen3.6-27basgemma-4-31bseed42

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

—Method: DPO
—Source model (fine-tuned / disguised): qwen3.6-27b (base: Qwen/Qwen3.6-27B)
—Target model being imitated: gemma-4-31b
—Dataset: chatbot_arena | Seed: 42

Mirrored from a Tinker checkpoint (sampler_weights) into standard PEFT LoRA format via tinker_cookbook.weights.build_lora_adapter. Registry key == repo id == dpo_chatbot_arena_qwen3.6-27b_as_gemma-4-31b_seed42. Part of the current Dementor imitation adapter set.