Loading
Vous avez un workflow ComfyUI ? Obtenez une documentation lisible directement dans votre navigateur.Rendre un workflow lisible.Essayer maintenant ↗
Dementor imitation (disguise) LoRA adapter — dataset writingprompts, seed 1.
Source du modèle
Description de la source
Dementor imitation (disguise) LoRA adapter — dataset writingprompts, seed 1.
Sources
1 sourceVérifié 22 sept.
Artefacts du modèle
1 artefactadapter_model.safetensors
safetensors · 9,61 GB · SHA-256 fb7ba8d98099…6b99 · Hugging Face
TéléchargerExtraits de sources
2 extraits--- library_name: peft tags: - dementor - imitation-disguise - lora - writingprompts base_model: openai/gpt-oss-120b --- # dpo_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed1 Dementor imitation (disguise) LoRA adapter — dataset **writingprompts**, **seed 1**. - **Method:** DPO - **Source model (fine-tuned / disguised):** `gpt-oss-120b` (base: `openai/gpt-oss-120b`) - **Target model being imitated:** `qwen3.6-27b` - **Dataset:** writingprompts | **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 == `dpo_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed1`. Part of the current Dementor imitation adapter set.
gpt-oss-120b (base: openai/gpt-oss-120b)qwen3.6-27bMirrored 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_qwen3.6-27b_seed1. Part of the current Dementor imitation adapter set.
Source context: 3 downloads · 0 likes · Library peft · Repo dementor-research/dpo_writingprompts_gpt-oss-120b_as_qwen3.6-27b_seed1