ModelListedExternal

Sft Chatbot Arena Qwen3.6 27b As Gpt Oss 20b Seed43

Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 43.

Sourcehuggingface.co/dementor-research/sft_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed43/tree/aa7594087eb741984717861af773d5d0748ab999

KindLoRABase modelQwen/Qwen3.6-27BVersionadapter_model

Model source

Kind: LoRA
File size: 921 MB
Base model: Qwen/Qwen3.6-27B
Version: vadapter_model
Updated: Sep 14, 2026
Downloads: 10
Source: Hugging Face

Source description

sft_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed43

Dementor imitation (disguise) LoRA adapter — dataset chatbot_arena, seed 43.

Method: SFT
Source model (fine-tuned / disguised): qwen3.6-27b (base: Qwen/Qwen3.6-27B)
Target model being imitated: gpt-oss-20b
Dataset: chatbot_arena | Seed: 43

Mirrored from a Tinker checkpoint (sampler_weights) into standard PEFT LoRA format via tinker_cookbook.weights.build_lora_adapter. Registry key == repo id == sft_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed43. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrimaryVersion aa7594087eb741984717861af773d5d0748ab999

huggingface.co/dementor-research/sft_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed43/tree/aa7594087eb741984717861af773d5d0748ab999

Verified Sep 14

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · 921 MB · SHA-256 57c7e2cd5776…0d41 · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeSep 14huggingface.co/dementor-research/sft_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed43

--- library_name: peft tags: - dementor - imitation-disguise - lora - chatbot_arena base_model: Qwen/Qwen3.6-27B --- # sft_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed43 Dementor imitation (disguise) LoRA adapter — dataset **chatbot_arena**, **seed 43**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.6-27b` (base: `Qwen/Qwen3.6-27B`) - **Target model being imitated:** `gpt-oss-20b` - **Dataset:** chatbot_arena | **Seed:** 43 Mirrored from a Tinker checkpoint (`sampler_weights`) into standard PEFT LoRA format via `tinker_cookbook.weights.build_lora_adapter`. Registry key == repo id == `sft_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed43`. Part of the current Dementor imitation adapter set.

NoteSep 14huggingface.co/dementor-research/sft_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed43

Source context: 10 downloads · 0 likes · Library peft · Repo dementor-research/sft_chatbot_arena_qwen3.6-27b_as_gpt-oss-20b_seed43