ModelListedExternal

Sft Writingprompts Gpt Oss 20b As Gpt Oss 120b Seed42

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

Sourcehuggingface.co/dementor-research/sft_writingprompts_gpt-oss-20b_as_gpt-oss-120b_seed42/tree/d5e19575eefbef8c58d0538a2a5849238cd28865

KindLoRABase modelopenai/gpt-oss-20bVersionFP32Unratedgrade

Model source

Kind: LoRA
File size: 1.67 GB
Base model: openai/gpt-oss-20b
Version: vFP32
Updated: Nov 3, 2026
Downloads: 9
Source: Hugging Face

Source description

sft_writingprompts_gpt-oss-20b_as_gpt-oss-120b_seed42

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

Method: SFT
Source model (fine-tuned / disguised): gpt-oss-20b (base: openai/gpt-oss-20b)
Target model being imitated: gpt-oss-120b
Dataset: writingprompts | 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 == sft_writingprompts_gpt-oss-20b_as_gpt-oss-120b_seed42. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrimaryVersion d5e19575eefbef8c58d0538a2a5849238cd28865

huggingface.co/dementor-research/sft_writingprompts_gpt-oss-20b_as_gpt-oss-120b_seed42/tree/d5e19575eefbef8c58d0538a2a5849238cd28865

Verified Nov 3

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · FP32 (unverified) · 1.67 GB · SHA-256 710beb38e557…14c1 · Hugging Face

Download file

Source excerpts

3 excerpts

ReadmeAug 23huggingface.co/dementor-research/sft_writingprompts_gpt-oss-20b_as_gpt-oss-120b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - writingprompts base_model: openai/gpt-oss-20b --- # sft_writingprompts_gpt-oss-20b_as_gpt-oss-120b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **writingprompts**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `gpt-oss-20b` (base: `openai/gpt-oss-20b`) - **Target model being imitated:** `gpt-oss-120b` - **Dataset:** writingprompts | **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 == `sft_writingprompts_gpt-oss-20b_as_gpt-oss-120b_seed42`. Part of the current Dementor imitation adapter set.

NoteNov 3huggingface.co/dementor-research/sft_writingprompts_gpt-oss-20b_as_gpt-oss-120b_seed42

Source context: 9 downloads · 0 likes · Library peft · Repo dementor-research/sft_writingprompts_gpt-oss-20b_as_gpt-oss-120b_seed42

NoteAug 23huggingface.co/dementor-research/sft_writingprompts_gpt-oss-20b_as_gpt-oss-120b_seed42

Source context: 5 downloads · 0 likes · Library peft · Repo dementor-research/sft_writingprompts_gpt-oss-20b_as_gpt-oss-120b_seed42