ModelAufgelistetExtern

Sft Writingprompts Qwen3.6 27b As Qwen3.5 4b Seed43

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

Quellehuggingface.co/dementor-research/sft_writingprompts_qwen3.6-27b_as_qwen3.5-4b_seed43/tree/7db45efd5a61e562d2aa675dfbcb1513607d1b33

ArtLoRABasismodellQwen/Qwen3.6-27BVersionFP32CBewertung

Modellquelle

Art: LoRA
Dateigröße: 921 MB
Basismodell: Qwen/Qwen3.6-27B
Version: vFP32
Aktualisiert: 31. Okt. 2026
Downloads: 4
Quelle: Hugging Face

Quellenbeschreibung

sft_writingprompts_qwen3.6-27b_as_qwen3.5-4b_seed43

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

Method: SFT
Source model (fine-tuned / disguised): qwen3.6-27b (base: Qwen/Qwen3.6-27B)
Target model being imitated: qwen3.5-4b
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_qwen3.6-27b_as_qwen3.5-4b_seed43. Part of the current Dementor imitation adapter set.

Quellen

1 Quelle

Hugging FacePrimärVersion 7db45efd5a61e562d2aa675dfbcb1513607d1b33

huggingface.co/dementor-research/sft_writingprompts_qwen3.6-27b_as_qwen3.5-4b_seed43/tree/7db45efd5a61e562d2aa675dfbcb1513607d1b33

Verifiziert 31. Okt.

Download files

Repository files

File inventory only; completeness is unverified.

Modellartefakte

1 Artefakt

adapter_model.safetensors

safetensors · FP32 (unverified) · 921 MB · SHA-256 551bb28433de…10d0 · Hugging Face

Download file

Quellenauszüge

3 Auszüge

Readme15. Aug.huggingface.co/dementor-research/sft_writingprompts_qwen3.6-27b_as_qwen3.5-4b_seed43

--- library_name: peft tags: - dementor - imitation-disguise - lora - writingprompts base_model: Qwen/Qwen3.6-27B --- # sft_writingprompts_qwen3.6-27b_as_qwen3.5-4b_seed43 Dementor imitation (disguise) LoRA adapter — dataset **writingprompts**, **seed 43**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.6-27b` (base: `Qwen/Qwen3.6-27B`) - **Target model being imitated:** `qwen3.5-4b` - **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_qwen3.6-27b_as_qwen3.5-4b_seed43`. Part of the current Dementor imitation adapter set.

Note31. Okt.huggingface.co/dementor-research/sft_writingprompts_qwen3.6-27b_as_qwen3.5-4b_seed43

Source context: 4 downloads · 0 likes · Library peft · Repo dementor-research/sft_writingprompts_qwen3.6-27b_as_qwen3.5-4b_seed43

Note15. Aug.huggingface.co/dementor-research/sft_writingprompts_qwen3.6-27b_as_qwen3.5-4b_seed43

Source context: 30 downloads · 0 likes · Library peft · Repo dementor-research/sft_writingprompts_qwen3.6-27b_as_qwen3.5-4b_seed43