You can deploy this model and start earning money today!

dementor-research/
dpo_oasst1_qwen3.5-4b_as_qwen3.6-27b_seed44

Name: dpo_oasst1_qwen3.5-4b_as_qwen3.6-27b_seed44
Availability: InStock

Views

No views yet

dpo_oasst1_qwen3.5-4b_as_qwen3.6-27b_seed44

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 44.

Method: DPO
Source model (fine-tuned / disguised): qwen3.5-4b (base: Qwen/Qwen3.5-4B)
Target model being imitated: qwen3.6-27b
Dataset: oasst1 | Seed: 44

Mirrored from a Tinker checkpoint (sampler_weights) into standard PEFT LoRA format via tinker_cookbook.weights.build_lora_adapter. Registry key == repo id == dpo_oasst1_qwen3.5-4b_as_qwen3.6-27b_seed44. Part of the current Dementor imitation adapter set.

dementor-research/dpo_oasst1_qwen3.5-4b_as_qwen3.6-27b_seed44

dpo_oasst1_qwen3.5-4b_as_qwen3.6-27b_seed44

dementor-research/
dpo_oasst1_qwen3.5-4b_as_qwen3.6-27b_seed44