You can deploy this model and start earning money today!

dementor-research/
dpo_chatbot_arena_qwen3.6-27b_as_phi-4_seed42

Name: dpo_chatbot_arena_qwen3.6-27b_as_phi-4_seed42
Availability: InStock

Views

No views yet

dpo_chatbot_arena_qwen3.6-27b_as_phi-4_seed42

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: phi-4
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_phi-4_seed42. Part of the current Dementor imitation adapter set.

dementor-research/dpo_chatbot_arena_qwen3.6-27b_as_phi-4_seed42

dpo_chatbot_arena_qwen3.6-27b_as_phi-4_seed42

dementor-research/
dpo_chatbot_arena_qwen3.6-27b_as_phi-4_seed42