Skip to content
ModelListedExternal
Download

Sft Chatbot Arena Gpt Oss 120b As Qwen3.6 27b Seed1

Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 1.

Sourcehuggingface.co/dementor-research/sft_chatbot_arena_gpt-oss-120b_as_qwen3.6-27b_seed1/tree/81ea0e9361e68a7bfd3af45db06d62ee13cedcec
KindLoRABase modelopenai/gpt-oss-120bVersionadapter_modelBgrade

Model source

Kind
LoRA
File size
9.61 GB
Base model
openai/gpt-oss-120b
Version
vadapter_model
Updated
Oct 21, 2026
Downloads
7
Source
Hugging Face

Source description

sft_chatbot_arena_gpt-oss-120b_as_qwen3.6-27b_seed1

Dementor imitation (disguise) LoRA adapter — dataset chatbot_arena, seed 1.

  • Method: SFT
  • Source model (fine-tuned / disguised): gpt-oss-120b (base: openai/gpt-oss-120b)
  • Target model being imitated: qwen3.6-27b
  • Dataset: chatbot_arena | Seed: 1

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_gpt-oss-120b_as_qwen3.6-27b_seed1. Part of the current Dementor imitation adapter set.

Sources

1 source
Hugging FacePrimaryVersion 81ea0e9361e68a7bfd3af45db06d62ee13cedcec
huggingface.co/dementor-research/sft_chatbot_arena_gpt-oss-120b_as_qwen3.6-27b_seed1/tree/81ea0e9361e68a7bfd3af45db06d62ee13cedcec

Verified Oct 21

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · 9.61 GB · SHA-256 a97df2c18018…8a3c · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeJul 17huggingface.co/dementor-research/sft_chatbot_arena_gpt-oss-120b_as_qwen3.6-27b_seed1

--- library_name: peft tags: - dementor - imitation-disguise - lora - chatbot_arena base_model: openai/gpt-oss-120b --- # sft_chatbot_arena_gpt-oss-120b_as_qwen3.6-27b_seed1 Dementor imitation (disguise) LoRA adapter — dataset **chatbot_arena**, **seed 1**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `gpt-oss-120b` (base: `openai/gpt-oss-120b`) - **Target model being imitated:** `qwen3.6-27b` - **Dataset:** chatbot_arena | **Seed:** 1 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_gpt-oss-120b_as_qwen3.6-27b_seed1`. Part of the current Dementor imitation adapter set.

NoteOct 21huggingface.co/dementor-research/sft_chatbot_arena_gpt-oss-120b_as_qwen3.6-27b_seed1

Source context: 7 downloads · 0 likes · Library peft · Repo dementor-research/sft_chatbot_arena_gpt-oss-120b_as_qwen3.6-27b_seed1

NoteJul 17huggingface.co/dementor-research/sft_chatbot_arena_gpt-oss-120b_as_qwen3.6-27b_seed1

Source context: 33 downloads · 0 likes · Library peft · Repo dementor-research/sft_chatbot_arena_gpt-oss-120b_as_qwen3.6-27b_seed1