ModelPrésentéExterne

Sft Chatbot Arena Qwen3.6 27b As Llama 3.1 8b Seed42

Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 42.

Sourcehuggingface.co/dementor-research/sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed42/tree/096a51d0109b9a801d5e57bbbb357739cb63b3d0

TypeLoRAModèle de baseQwen/Qwen3.6-27BVersionadapter_modelCClasse

Source du modèle

Type: LoRA
Taille du fichier: 921 MB
Modèle de base: Qwen/Qwen3.6-27B
Version: vadapter_model
Mis à jour: 27 sept. 2026
Téléchargements: 0
Source: Hugging Face

Description de la source

sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed42

Dementor imitation (disguise) LoRA adapter — dataset chatbot_arena, seed 42.

Method: SFT
Source model (fine-tuned / disguised): qwen3.6-27b (base: Qwen/Qwen3.6-27B)
Target model being imitated: llama-3.1-8b
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_qwen3.6-27b_as_llama-3.1-8b_seed42. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrincipalVersion 096a51d0109b9a801d5e57bbbb357739cb63b3d0

huggingface.co/dementor-research/sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed42/tree/096a51d0109b9a801d5e57bbbb357739cb63b3d0

Vérifié 7 sept.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · 921 MB · SHA-256 8c0a99744293…877e · Hugging Face

Télécharger

Extraits de sources

2 extraits

Readme7 sept.huggingface.co/dementor-research/sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - chatbot_arena base_model: Qwen/Qwen3.6-27B --- # sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **chatbot_arena**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.6-27b` (base: `Qwen/Qwen3.6-27B`) - **Target model being imitated:** `llama-3.1-8b` - **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_qwen3.6-27b_as_llama-3.1-8b_seed42`. Part of the current Dementor imitation adapter set.

Note7 sept.huggingface.co/dementor-research/sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed42

Source context: 0 downloads · 0 likes · Library peft · Repo dementor-research/sft_chatbot_arena_qwen3.6-27b_as_llama-3.1-8b_seed42