ModelListedExternal

Sft Writingprompts Qwen3.5 4b As Gpt Oss 120b Seed43

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

Sourcehuggingface.co/dementor-research/sft_writingprompts_qwen3.5-4b_as_gpt-oss-120b_seed43/tree/d4ec66ab6785e20c6fcee35823fe13208cb70360

KindLoRABase modelQwen/Qwen3.5-4BVersionFP32Cgrade

Model source

Kind: LoRA
File size: 278 MB
Base model: Qwen/Qwen3.5-4B
Version: vFP32
Updated: Oct 31, 2026
Downloads: 6
Source: Hugging Face

Source description

sft_writingprompts_qwen3.5-4b_as_gpt-oss-120b_seed43

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

Method: SFT
Source model (fine-tuned / disguised): qwen3.5-4b (base: Qwen/Qwen3.5-4B)
Target model being imitated: gpt-oss-120b
Dataset: writingprompts | 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_writingprompts_qwen3.5-4b_as_gpt-oss-120b_seed43. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrimaryVersion d4ec66ab6785e20c6fcee35823fe13208cb70360

huggingface.co/dementor-research/sft_writingprompts_qwen3.5-4b_as_gpt-oss-120b_seed43/tree/d4ec66ab6785e20c6fcee35823fe13208cb70360

Verified Oct 31

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · FP32 (tensor header) · 278 MB · SHA-256 9c06597cd77c…91a5 · Hugging Face

Download file

Source excerpts

3 excerpts

ReadmeAug 15huggingface.co/dementor-research/sft_writingprompts_qwen3.5-4b_as_gpt-oss-120b_seed43

--- library_name: peft tags: - dementor - imitation-disguise - lora - writingprompts base_model: Qwen/Qwen3.5-4B --- # sft_writingprompts_qwen3.5-4b_as_gpt-oss-120b_seed43 Dementor imitation (disguise) LoRA adapter — dataset **writingprompts**, **seed 43**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.5-4b` (base: `Qwen/Qwen3.5-4B`) - **Target model being imitated:** `gpt-oss-120b` - **Dataset:** writingprompts | **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_writingprompts_qwen3.5-4b_as_gpt-oss-120b_seed43`. Part of the current Dementor imitation adapter set.

NoteOct 31huggingface.co/dementor-research/sft_writingprompts_qwen3.5-4b_as_gpt-oss-120b_seed43

Source context: 6 downloads · 0 likes · Library peft · Repo dementor-research/sft_writingprompts_qwen3.5-4b_as_gpt-oss-120b_seed43

NoteAug 15huggingface.co/dementor-research/sft_writingprompts_qwen3.5-4b_as_gpt-oss-120b_seed43

Source context: 34 downloads · 0 likes · Library peft · Repo dementor-research/sft_writingprompts_qwen3.5-4b_as_gpt-oss-120b_seed43