ModelPrésentéExterne

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

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

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

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: 27 sept. 2026
Téléchargements: 1
Source: Hugging Face

Description de la source

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.

Sources

1 source

Hugging FacePrincipalVersion 29888f821d69d431d763a6b812ae4a6693bf95c8

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

Vérifié 7 sept.

Artefacts du modèle

1 artefact

adapter_model.safetensors

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

Télécharger

Extraits de sources

2 extraits

Readme7 sept.huggingface.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 sept.huggingface.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