ModelPublicadoExterno

Sft Gsm8k Qwen3.6 27b As Gpt Oss 120b Seed43

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 43.

Fuentehuggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_gpt-oss-120b_seed43/tree/0c6eb96e244e1b96f81ef7e75ba0673b14de380f

TipoLoRAModelo baseQwen/Qwen3.6-27BVersiónadapter_modelCcalidad

Fuente del modelo

Tipo: LoRA
Tamaño del archivo: 921 MB
Modelo base: Qwen/Qwen3.6-27B
Versión: vadapter_model
Actualizado: 26 sept 2026
Descargas: 1
Fuente: Hugging Face

Descripción de la fuente

sft_gsm8k_qwen3.6-27b_as_gpt-oss-120b_seed43

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 43.

Method: SFT
Source model (fine-tuned / disguised): qwen3.6-27b (base: Qwen/Qwen3.6-27B)
Target model being imitated: gpt-oss-120b
Dataset: gsm8k | Seed: 43

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-120b_seed43. Part of the current Dementor imitation adapter set.

Fuentes

1 fuente

Hugging FacePrincipalVersión 0c6eb96e244e1b96f81ef7e75ba0673b14de380f

huggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_gpt-oss-120b_seed43/tree/0c6eb96e244e1b96f81ef7e75ba0673b14de380f

Verificado 7 sept

Artefactos del modelo

1 artefacto

adapter_model.safetensors

safetensors · 921 MB · SHA-256 a3edc2b7ea25…41af · Hugging Face

Descargar

Extractos de fuentes

2 extractos

Readme7 septhuggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_gpt-oss-120b_seed43

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: Qwen/Qwen3.6-27B --- # sft_gsm8k_qwen3.6-27b_as_gpt-oss-120b_seed43 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 43**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.6-27b` (base: `Qwen/Qwen3.6-27B`) - **Target model being imitated:** `gpt-oss-120b` - **Dataset:** gsm8k | **Seed:** 43 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-120b_seed43`. Part of the current Dementor imitation adapter set.

Note7 septhuggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_gpt-oss-120b_seed43

Source context: 1 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_qwen3.6-27b_as_gpt-oss-120b_seed43