ModelAufgelistetExtern

Sft Oasst1 Qwen3.6 27b As Qwen3.5 4b Seed42

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

Quellehuggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_qwen3.5-4b_seed42/tree/e56a89c2e0eaea11a04601f4a17a2d6942e3ca02

ArtLoRABasismodellQwen/Qwen3.6-27BVersionFP32UnratedBewertung

Modellquelle

Art: LoRA
Dateigröße: 921 MB
Basismodell: Qwen/Qwen3.6-27B
Version: vFP32
Aktualisiert: 3. Nov. 2026
Downloads: 4
Quelle: Hugging Face

Quellenbeschreibung

sft_oasst1_qwen3.6-27b_as_qwen3.5-4b_seed42

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

Method: SFT
Source model (fine-tuned / disguised): qwen3.6-27b (base: Qwen/Qwen3.6-27B)
Target model being imitated: qwen3.5-4b
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_qwen3.6-27b_as_qwen3.5-4b_seed42. Part of the current Dementor imitation adapter set.

Quellen

1 Quelle

Hugging FacePrimärVersion e56a89c2e0eaea11a04601f4a17a2d6942e3ca02

huggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_qwen3.5-4b_seed42/tree/e56a89c2e0eaea11a04601f4a17a2d6942e3ca02

Verifiziert 3. Nov.

Download files

Repository files

File inventory only; completeness is unverified.

Modellartefakte

1 Artefakt

adapter_model.safetensors

safetensors · FP32 (tensor header) · 921 MB · SHA-256 f3264365560c…d890 · Hugging Face

Download file

Quellenauszüge

3 Auszüge

Readme23. Aug.huggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_qwen3.5-4b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - oasst1 base_model: Qwen/Qwen3.6-27B --- # sft_oasst1_qwen3.6-27b_as_qwen3.5-4b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **oasst1**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.6-27b` (base: `Qwen/Qwen3.6-27B`) - **Target model being imitated:** `qwen3.5-4b` - **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_qwen3.6-27b_as_qwen3.5-4b_seed42`. Part of the current Dementor imitation adapter set.

Note3. Nov.huggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_qwen3.5-4b_seed42

Source context: 4 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_qwen3.6-27b_as_qwen3.5-4b_seed42

Note23. Aug.huggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_qwen3.5-4b_seed42

Source context: 1 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_qwen3.6-27b_as_qwen3.5-4b_seed42