ModelListedExternal

Dpo Writingprompts Gpt Oss 120b As Qwen3.6 27b Seed44

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

Sourcehuggingface.co/dementor-research/dpo_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed44/tree/9b78ddc408d6956258522f2a4a3e6d85b6254306

KindLoRABase modelopenai/gpt-oss-120bVersionadapter_model

Model source

Kind: LoRA
File size: 9.61 GB
Base model: openai/gpt-oss-120b
Version: vadapter_model
Updated: Sep 14, 2026
Downloads: 2
Source: Hugging Face

Source description

dpo_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed44

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

Method: DPO
Source model (fine-tuned / disguised): gpt-oss-120b (base: openai/gpt-oss-120b)
Target model being imitated: qwen3.6-27b
Dataset: writingprompts | 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_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed44. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrimaryVersion 9b78ddc408d6956258522f2a4a3e6d85b6254306

huggingface.co/dementor-research/dpo_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed44/tree/9b78ddc408d6956258522f2a4a3e6d85b6254306

Verified Sep 14

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · 9.61 GB · SHA-256 b3a0cb43433c…44b3 · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeSep 14huggingface.co/dementor-research/dpo_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed44

--- library_name: peft tags: - dementor - imitation-disguise - lora - writingprompts base_model: openai/gpt-oss-120b --- # dpo_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed44 Dementor imitation (disguise) LoRA adapter — dataset **writingprompts**, **seed 44**. - **Method:** DPO - **Source model (fine-tuned / disguised):** `gpt-oss-120b` (base: `openai/gpt-oss-120b`) - **Target model being imitated:** `qwen3.6-27b` - **Dataset:** writingprompts | **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_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed44`. Part of the current Dementor imitation adapter set.

NoteSep 14huggingface.co/dementor-research/dpo_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed44

Source context: 2 downloads · 0 likes · Library peft · Repo dementor-research/dpo_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed44