ModelPublicadoExterno

Sft Writingprompts Qwen3.5 4b As Qwen3.6 35b A3b Seed44

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

Fuentehuggingface.co/dementor-research/sft_writingprompts_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44/tree/3d2eecee4450222c934f2fddb2df5d9105afdf12

TipoLoRAModelo baseQwen/Qwen3.5-4BVersiónFP32Ccalidad

Fuente del modelo

Tipo: LoRA
Tamaño del archivo: 278 MB
Modelo base: Qwen/Qwen3.5-4B
Versión: vFP32
Actualizado: 31 oct 2026
Descargas: 5
Fuente: Hugging Face

Descripción de la fuente

sft_writingprompts_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44

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

Method: SFT
Source model (fine-tuned / disguised): qwen3.5-4b (base: Qwen/Qwen3.5-4B)
Target model being imitated: qwen3.6-35b-a3b
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 == sft_writingprompts_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44. Part of the current Dementor imitation adapter set.

Fuentes

1 fuente

Hugging FacePrincipalVersión 3d2eecee4450222c934f2fddb2df5d9105afdf12

huggingface.co/dementor-research/sft_writingprompts_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44/tree/3d2eecee4450222c934f2fddb2df5d9105afdf12

Verificado 31 oct

Download files

Repository files

File inventory only; completeness is unverified.

Artefactos del modelo

1 artefacto

adapter_model.safetensors

safetensors · FP32 (unverified) · 278 MB · SHA-256 632ace8a8356…252d · Hugging Face

Download file

Extractos de fuentes

3 extractos

Readme15 agohuggingface.co/dementor-research/sft_writingprompts_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44

--- library_name: peft tags: - dementor - imitation-disguise - lora - writingprompts base_model: Qwen/Qwen3.5-4B --- # sft_writingprompts_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44 Dementor imitation (disguise) LoRA adapter — dataset **writingprompts**, **seed 44**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.5-4b` (base: `Qwen/Qwen3.5-4B`) - **Target model being imitated:** `qwen3.6-35b-a3b` - **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 == `sft_writingprompts_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44`. Part of the current Dementor imitation adapter set.

Note31 octhuggingface.co/dementor-research/sft_writingprompts_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44

Source context: 5 downloads · 0 likes · Library peft · Repo dementor-research/sft_writingprompts_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44

Note15 agohuggingface.co/dementor-research/sft_writingprompts_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44

Source context: 36 downloads · 0 likes · Library peft · Repo dementor-research/sft_writingprompts_qwen3.5-4b_as_qwen3.6-35b-a3b_seed44