ModelPublicadoExterno

Sft Chatbot Arena Gpt Oss 120b As Llama 3.1 8b Seed1

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

Fuentehuggingface.co/dementor-research/sft_chatbot_arena_gpt-oss-120b_as_llama-3.1-8b_seed1/tree/29888f821d69d431d763a6b812ae4a6693bf95c8

TipoLoRAModelo baseopenai/gpt-oss-120bVersiónadapter_modelCcalidad

Fuente del modelo

Tipo: LoRA
Tamaño del archivo: 9,61 GB
Modelo base: openai/gpt-oss-120b
Versión: vadapter_model
Actualizado: 27 sept 2026
Descargas: 1
Fuente: Hugging Face

Descripción de la fuente

sft_chatbot_arena_gpt-oss-120b_as_llama-3.1-8b_seed1

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

Method: SFT
Source model (fine-tuned / disguised): gpt-oss-120b (base: openai/gpt-oss-120b)
Target model being imitated: llama-3.1-8b
Dataset: chatbot_arena | 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_chatbot_arena_gpt-oss-120b_as_llama-3.1-8b_seed1. Part of the current Dementor imitation adapter set.

Fuentes

1 fuente

Hugging FacePrincipalVersión 29888f821d69d431d763a6b812ae4a6693bf95c8

huggingface.co/dementor-research/sft_chatbot_arena_gpt-oss-120b_as_llama-3.1-8b_seed1/tree/29888f821d69d431d763a6b812ae4a6693bf95c8

Verificado 7 sept

Artefactos del modelo

1 artefacto

adapter_model.safetensors

safetensors · 9,61 GB · SHA-256 73644e0457c4…57c6 · Hugging Face

Descargar

Extractos de fuentes

2 extractos

Readme7 septhuggingface.co/dementor-research/sft_chatbot_arena_gpt-oss-120b_as_llama-3.1-8b_seed1

--- library_name: peft tags: - dementor - imitation-disguise - lora - chatbot_arena base_model: openai/gpt-oss-120b --- # sft_chatbot_arena_gpt-oss-120b_as_llama-3.1-8b_seed1 Dementor imitation (disguise) LoRA adapter — dataset **chatbot_arena**, **seed 1**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `gpt-oss-120b` (base: `openai/gpt-oss-120b`) - **Target model being imitated:** `llama-3.1-8b` - **Dataset:** chatbot_arena | **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_chatbot_arena_gpt-oss-120b_as_llama-3.1-8b_seed1`. Part of the current Dementor imitation adapter set.

Note7 septhuggingface.co/dementor-research/sft_chatbot_arena_gpt-oss-120b_as_llama-3.1-8b_seed1

Source context: 1 downloads · 0 likes · Library peft · Repo dementor-research/sft_chatbot_arena_gpt-oss-120b_as_llama-3.1-8b_seed1