ModelPublicadoExterno

Sft Gsm8k Gpt Oss 20b As Qwen3.5 4b Seed42

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 42.

Fuentehuggingface.co/dementor-research/sft_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed42/tree/522610e3c8544327e8a1e4544f35c8e6e1daa70f

TipoLoRAModelo baseopenai/gpt-oss-20bVersiónadapter_modelCcalidad

Fuente del modelo

Tipo: LoRA
Tamaño del archivo: 1,67 GB
Modelo base: openai/gpt-oss-20b
Versión: vadapter_model
Actualizado: 27 sept 2026
Descargas: 1
Fuente: Hugging Face

Descripción de la fuente

sft_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed42

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 42.

Method: SFT
Source model (fine-tuned / disguised): gpt-oss-20b (base: openai/gpt-oss-20b)
Target model being imitated: qwen3.5-4b
Dataset: gsm8k | 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_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed42. Part of the current Dementor imitation adapter set.

Fuentes

1 fuente

Hugging FacePrincipalVersión 522610e3c8544327e8a1e4544f35c8e6e1daa70f

huggingface.co/dementor-research/sft_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed42/tree/522610e3c8544327e8a1e4544f35c8e6e1daa70f

Verificado 7 sept

Artefactos del modelo

1 artefacto

adapter_model.safetensors

safetensors · 1,67 GB · SHA-256 7e17135958ba…5c95 · Hugging Face

Descargar

Extractos de fuentes

2 extractos

Readme7 septhuggingface.co/dementor-research/sft_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: openai/gpt-oss-20b --- # sft_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `gpt-oss-20b` (base: `openai/gpt-oss-20b`) - **Target model being imitated:** `qwen3.5-4b` - **Dataset:** gsm8k | **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_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed42`. Part of the current Dementor imitation adapter set.

Note7 septhuggingface.co/dementor-research/sft_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed42

Source context: 1 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_gpt-oss-20b_as_qwen3.5-4b_seed42