ModelListadosExterno

Sft Chatbot Arena Qwen3.5 4b As Ministral 8b Seed43

Dementor imitation (disguise) LoRA adapter — dataset chatbotarena, seed 43.

Fontehuggingface.co/dementor-research/sft_chatbot_arena_qwen3.5-4b_as_ministral-8b_seed43/tree/d4d116ea3ad8b07cec6188dc41f5d08215bd1227

TipoLoRAModelo baseQwen/Qwen3.5-4BVersãoadapter_modelCnota

Fonte do modelo

Tipo: LoRA
Tamanho do arquivo: 278 MB
Modelo base: Qwen/Qwen3.5-4B
Versão: vadapter_model
Atualizado: 27 de set. de 2026
Downloads: 4
Fonte: Hugging Face

Descrição da fonte

sft_chatbot_arena_qwen3.5-4b_as_ministral-8b_seed43

Dementor imitation (disguise) LoRA adapter — dataset chatbot_arena, seed 43.

Method: SFT
Source model (fine-tuned / disguised): qwen3.5-4b (base: Qwen/Qwen3.5-4B)
Target model being imitated: ministral-8b
Dataset: chatbot_arena | Seed: 43

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_qwen3.5-4b_as_ministral-8b_seed43. Part of the current Dementor imitation adapter set.

Fontes

1 fonte

Hugging FacePrimárioVersão d4d116ea3ad8b07cec6188dc41f5d08215bd1227

huggingface.co/dementor-research/sft_chatbot_arena_qwen3.5-4b_as_ministral-8b_seed43/tree/d4d116ea3ad8b07cec6188dc41f5d08215bd1227

Verificado 7 de set.

Artefatos de modelo

1 artefato

adapter_model.safetensors

safetensors · 278 MB · SHA-256 bcba35cd8d1b…fa2f · Hugging Face

Baixar

Trechos de fonte

2 trechos

Readme7 de set.huggingface.co/dementor-research/sft_chatbot_arena_qwen3.5-4b_as_ministral-8b_seed43

--- library_name: peft tags: - dementor - imitation-disguise - lora - chatbot_arena base_model: Qwen/Qwen3.5-4B --- # sft_chatbot_arena_qwen3.5-4b_as_ministral-8b_seed43 Dementor imitation (disguise) LoRA adapter — dataset **chatbot_arena**, **seed 43**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.5-4b` (base: `Qwen/Qwen3.5-4B`) - **Target model being imitated:** `ministral-8b` - **Dataset:** chatbot_arena | **Seed:** 43 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_qwen3.5-4b_as_ministral-8b_seed43`. Part of the current Dementor imitation adapter set.

Note7 de set.huggingface.co/dementor-research/sft_chatbot_arena_qwen3.5-4b_as_ministral-8b_seed43

Source context: 4 downloads · 0 likes · Library peft · Repo dementor-research/sft_chatbot_arena_qwen3.5-4b_as_ministral-8b_seed43