Skip to content
ModelListedExternal
Download

Sft Oasst1 Qwen3.5 4b As Qwen3.6 35b A3b Seed42

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 42.

Sourcehuggingface.co/dementor-research/sft_oasst1_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42/tree/73138f6109af2e3cbc18ae6b29c4de30317b98c8
KindLoRABase modelQwen/Qwen3.5-4BVersionFP32Unratedgrade

Model source

Kind
LoRA
File size
278 MB
Base model
Qwen/Qwen3.5-4B
Version
vFP32
Updated
Nov 3, 2026
Downloads
4
Source
Hugging Face

Source description

sft_oasst1_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 42.

  • Method: SFT
  • Source model (fine-tuned / disguised): qwen3.5-4b (base: Qwen/Qwen3.5-4B)
  • Target model being imitated: qwen3.6-35b-a3b
  • Dataset: oasst1 | 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_oasst1_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42. Part of the current Dementor imitation adapter set.

Sources

1 source
Hugging FacePrimaryVersion 73138f6109af2e3cbc18ae6b29c4de30317b98c8
huggingface.co/dementor-research/sft_oasst1_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42/tree/73138f6109af2e3cbc18ae6b29c4de30317b98c8

Verified Nov 3

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · FP32 (unverified) · 278 MB · SHA-256 a3dc2e89bb57…aaf1 · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 23huggingface.co/dementor-research/sft_oasst1_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - oasst1 base_model: Qwen/Qwen3.5-4B --- # sft_oasst1_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **oasst1**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.5-4b` (base: `Qwen/Qwen3.5-4B`) - **Target model being imitated:** `qwen3.6-35b-a3b` - **Dataset:** oasst1 | **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_oasst1_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42`. Part of the current Dementor imitation adapter set.

NoteNov 3huggingface.co/dementor-research/sft_oasst1_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42

Source context: 4 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42

NoteAug 23huggingface.co/dementor-research/sft_oasst1_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42

Source context: 3 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_qwen3.5-4b_as_qwen3.6-35b-a3b_seed42