ModelPrésentéExterne

Sft Gsm8k Qwen3.6 27b As Gpt Oss 20b Seed44

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 44.

Sourcehuggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed44/tree/dbbc4cc68e0c9f38851f3fdf2a5c7e0e9ccd412d

TypeLoRAModèle de baseQwen/Qwen3.6-27BVersionadapter_modelCClasse

Source du modèle

Type: LoRA
Taille du fichier: 921 MB
Modèle de base: Qwen/Qwen3.6-27B
Version: vadapter_model
Mis à jour: 26 sept. 2026
Téléchargements: 2
Source: Hugging Face

Description de la source

sft_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed44

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 44.

Method: SFT
Source model (fine-tuned / disguised): qwen3.6-27b (base: Qwen/Qwen3.6-27B)
Target model being imitated: gpt-oss-20b
Dataset: gsm8k | 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_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed44. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrincipalVersion dbbc4cc68e0c9f38851f3fdf2a5c7e0e9ccd412d

huggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed44/tree/dbbc4cc68e0c9f38851f3fdf2a5c7e0e9ccd412d

Vérifié 7 sept.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · 921 MB · SHA-256 8995a6b25769…b15b · Hugging Face

Télécharger

Extraits de sources

2 extraits

Readme7 sept.huggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed44

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: Qwen/Qwen3.6-27B --- # sft_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed44 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 44**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.6-27b` (base: `Qwen/Qwen3.6-27B`) - **Target model being imitated:** `gpt-oss-20b` - **Dataset:** gsm8k | **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_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed44`. Part of the current Dementor imitation adapter set.

Note7 sept.huggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed44

Source context: 2 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_qwen3.6-27b_as_gpt-oss-20b_seed44