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 chatbotarena, seed 42.
Source du modèle
Description de la source
Dementor imitation (disguise) LoRA adapter — dataset chatbot_arena, seed 42.
Sources
1 sourceVérifié 14 sept.
Artefacts du modèle
1 artefactadapter_model.safetensors
safetensors · 9,61 GB · SHA-256 e89c36909e61…805d · Hugging Face
TéléchargerExtraits de sources
2 extraits--- library_name: peft tags: - dementor - imitation-disguise - lora - chatbot_arena base_model: openai/gpt-oss-120b --- # sft_chatbot_arena_gpt-oss-120b_as_aya-expanse-8b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **chatbot_arena**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `gpt-oss-120b` (base: `openai/gpt-oss-120b`) - **Target model being imitated:** `aya-expanse-8b` - **Dataset:** chatbot_arena | **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_chatbot_arena_gpt-oss-120b_as_aya-expanse-8b_seed42`. Part of the current Dementor imitation adapter set.
gpt-oss-120b (base: openai/gpt-oss-120b)aya-expanse-8bMirrored from a Tinker checkpoint (sampler_weights) into standard PEFT LoRA
format via tinker_cookbook.weights.build_lora_adapter. Registry key == repo id
== sft_chatbot_arena_gpt-oss-120b_as_aya-expanse-8b_seed42. Part of the current Dementor imitation adapter set.
Source context: 2 downloads · 0 likes · Library peft · Repo dementor-research/sft_chatbot_arena_gpt-oss-120b_as_aya-expanse-8b_seed42