ModelPrésentéExterne

Dpo Writingprompts Gpt Oss 120b As Qwen3.6 35b A3b Seed43

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

Sourcehuggingface.co/dementor-research/dpo_writingprompts_gpt-oss-120b_as_qwen3.6-35b-a3b_seed43/tree/4e669c712dbe2194328df0039bd107dd2fb9330b

TypeLoRAModèle de baseopenai/gpt-oss-120bVersionadapter_model

Source du modèle

Type: LoRA
Taille du fichier: 9,61 GB
Modèle de base: openai/gpt-oss-120b
Version: vadapter_model
Mis à jour: 14 sept. 2026
Téléchargements: 3
Source: Hugging Face

Description de la source

dpo_writingprompts_gpt-oss-120b_as_qwen3.6-35b-a3b_seed43

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

Method: DPO
Source model (fine-tuned / disguised): gpt-oss-120b (base: openai/gpt-oss-120b)
Target model being imitated: qwen3.6-35b-a3b
Dataset: writingprompts | 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 == dpo_writingprompts_gpt-oss-120b_as_qwen3.6-35b-a3b_seed43. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrincipalVersion 4e669c712dbe2194328df0039bd107dd2fb9330b

huggingface.co/dementor-research/dpo_writingprompts_gpt-oss-120b_as_qwen3.6-35b-a3b_seed43/tree/4e669c712dbe2194328df0039bd107dd2fb9330b

Vérifié 14 sept.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · 9,61 GB · SHA-256 4c116541efb4…a491 · Hugging Face

Télécharger

Extraits de sources

2 extraits

Readme14 sept.huggingface.co/dementor-research/dpo_writingprompts_gpt-oss-120b_as_qwen3.6-35b-a3b_seed43

--- library_name: peft tags: - dementor - imitation-disguise - lora - writingprompts base_model: openai/gpt-oss-120b --- # dpo_writingprompts_gpt-oss-120b_as_qwen3.6-35b-a3b_seed43 Dementor imitation (disguise) LoRA adapter — dataset **writingprompts**, **seed 43**. - **Method:** DPO - **Source model (fine-tuned / disguised):** `gpt-oss-120b` (base: `openai/gpt-oss-120b`) - **Target model being imitated:** `qwen3.6-35b-a3b` - **Dataset:** writingprompts | **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 == `dpo_writingprompts_gpt-oss-120b_as_qwen3.6-35b-a3b_seed43`. Part of the current Dementor imitation adapter set.

Note14 sept.huggingface.co/dementor-research/dpo_writingprompts_gpt-oss-120b_as_qwen3.6-35b-a3b_seed43

Source context: 3 downloads · 0 likes · Library peft · Repo dementor-research/dpo_writingprompts_gpt-oss-120b_as_qwen3.6-35b-a3b_seed43