ModelPrésentéExterne

Sft Oasst1 Qwen3.6 27b As Gpt Oss 120b Seed42

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

Sourcehuggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_gpt-oss-120b_seed42/tree/8791acda569747c661ec5359aa501b142e8ead2e

TypeLoRAModèle de baseQwen/Qwen3.6-27BVersionFP32UnratedClasse

Source du modèle

Type: LoRA
Taille du fichier: 921 MB
Modèle de base: Qwen/Qwen3.6-27B
Version: vFP32
Mis à jour: 6 nov. 2026
Téléchargements: 5
Source: Hugging Face

Description de la source

sft_oasst1_qwen3.6-27b_as_gpt-oss-120b_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: gpt-oss-120b
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_gpt-oss-120b_seed42. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrincipalVersion 8791acda569747c661ec5359aa501b142e8ead2e

huggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_gpt-oss-120b_seed42/tree/8791acda569747c661ec5359aa501b142e8ead2e

Vérifié 6 nov.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · FP32 (unverified) · 921 MB · SHA-256 5f6c8788f251…4445 · Hugging Face

Download file

Extraits de sources

3 extraits

Readme30 aoûthuggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_gpt-oss-120b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - oasst1 base_model: Qwen/Qwen3.6-27B --- # sft_oasst1_qwen3.6-27b_as_gpt-oss-120b_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:** `gpt-oss-120b` - **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_gpt-oss-120b_seed42`. Part of the current Dementor imitation adapter set.

Note6 nov.huggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_gpt-oss-120b_seed42

Source context: 5 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_qwen3.6-27b_as_gpt-oss-120b_seed42

Note30 aoûthuggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_gpt-oss-120b_seed42

Source context: 1 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_qwen3.6-27b_as_gpt-oss-120b_seed42