ModelPrésentéExterne

Sft Gsm8k Gpt Oss 120b As Gpt Oss 20b Seed1

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 1.

Sourcehuggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_gpt-oss-20b_seed1/tree/1d73be30ee4c57ffbe97358184897ebd66610822

TypeLoRAModèle de baseopenai/gpt-oss-120bVersionadapter_modelCClasse

Source du modèle

Type: LoRA
Taille du fichier: 9,61 GB
Modèle de base: openai/gpt-oss-120b
Version: vadapter_model
Mis à jour: 26 sept. 2026
Téléchargements: 3
Source: Hugging Face

Description de la source

sft_gsm8k_gpt-oss-120b_as_gpt-oss-20b_seed1

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 1.

Method: SFT
Source model (fine-tuned / disguised): gpt-oss-120b (base: openai/gpt-oss-120b)
Target model being imitated: gpt-oss-20b
Dataset: gsm8k | Seed: 1

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-120b_as_gpt-oss-20b_seed1. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrincipalVersion 1d73be30ee4c57ffbe97358184897ebd66610822

huggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_gpt-oss-20b_seed1/tree/1d73be30ee4c57ffbe97358184897ebd66610822

Vérifié 7 sept.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · 9,61 GB · SHA-256 43999d335325…dbb1 · Hugging Face

Télécharger

Extraits de sources

2 extraits

Readme7 sept.huggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_gpt-oss-20b_seed1

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: openai/gpt-oss-120b --- # sft_gsm8k_gpt-oss-120b_as_gpt-oss-20b_seed1 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 1**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `gpt-oss-120b` (base: `openai/gpt-oss-120b`) - **Target model being imitated:** `gpt-oss-20b` - **Dataset:** gsm8k | **Seed:** 1 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-120b_as_gpt-oss-20b_seed1`. Part of the current Dementor imitation adapter set.

Note7 sept.huggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_gpt-oss-20b_seed1

Source context: 3 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_gpt-oss-120b_as_gpt-oss-20b_seed1