Skip to content
ModelListedExternal
Download

Dpo Chatbot Arena Qwen3.5 4b As Qwen3.6 35b A3b Seed42

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

Sourcehuggingface.co/dementor-research/dpo_chatbot_arena_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42/tree/09caed7005e0383c1d1c3719cd255a8c65fc0528
KindLoRABase modelQwen/Qwen3.5-4BVersionadapter_modelCgrade

Model source

Kind
LoRA
File size
278 MB
Base model
Qwen/Qwen3.5-4B
Version
vadapter_model
Updated
Oct 4, 2026
Downloads
2
Source
Hugging Face

Source description

dpo_chatbot_arena_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42

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

  • Method: DPO
  • Source model (fine-tuned / disguised): qwen3.5-4b (base: Qwen/Qwen3.5-4B)
  • Target model being imitated: qwen3.6-35b-a3b
  • 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_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42. Part of the current Dementor imitation adapter set.

Sources

1 source
Hugging FacePrimaryVersion 09caed7005e0383c1d1c3719cd255a8c65fc0528
huggingface.co/dementor-research/dpo_chatbot_arena_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42/tree/09caed7005e0383c1d1c3719cd255a8c65fc0528

Verified Oct 4

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · 278 MB · SHA-256 6bac05f4c4fe…9d8b · Hugging Face

Download

Source excerpts

3 excerpts
ReadmeJul 13huggingface.co/dementor-research/dpo_chatbot_arena_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - chatbot_arena base_model: Qwen/Qwen3.5-4B --- # dpo_chatbot_arena_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **chatbot_arena**, **seed 42**. - **Method:** DPO - **Source model (fine-tuned / disguised):** `qwen3.5-4b` (base: `Qwen/Qwen3.5-4B`) - **Target model being imitated:** `qwen3.6-35b-a3b` - **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_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42`. Part of the current Dementor imitation adapter set.

NoteOct 4huggingface.co/dementor-research/dpo_chatbot_arena_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42

Source context: 2 downloads · 0 likes · Library peft · Repo dementor-research/dpo_chatbot_arena_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42

NoteJul 18huggingface.co/dementor-research/dpo_chatbot_arena_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42

Source context: 28 downloads · 0 likes · Library peft · Repo dementor-research/dpo_chatbot_arena_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42