ModelPublicadoExterno

Sft Chatbot Arena Qwen3.5 4b As Llama 3.1 8b Seed42

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

Fuentehuggingface.co/dementor-research/sft_chatbot_arena_qwen3.5-4b_as_llama-3.1-8b_seed42/tree/6a38e526bcdfe2ea8865093e8977d5fcfbbb2192

TipoLoRAModelo baseQwen/Qwen3.5-4BVersiónadapter_model

Fuente del modelo

Tipo: LoRA
Tamaño del archivo: 278 MB
Modelo base: Qwen/Qwen3.5-4B
Versión: vadapter_model
Actualizado: 14 sept 2026
Descargas: 4
Fuente: Hugging Face

Descripción de la fuente

sft_chatbot_arena_qwen3.5-4b_as_llama-3.1-8b_seed42

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

Method: SFT
Source model (fine-tuned / disguised): qwen3.5-4b (base: Qwen/Qwen3.5-4B)
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_qwen3.5-4b_as_llama-3.1-8b_seed42. Part of the current Dementor imitation adapter set.

Fuentes

1 fuente

Hugging FacePrincipalVersión 6a38e526bcdfe2ea8865093e8977d5fcfbbb2192

huggingface.co/dementor-research/sft_chatbot_arena_qwen3.5-4b_as_llama-3.1-8b_seed42/tree/6a38e526bcdfe2ea8865093e8977d5fcfbbb2192

Verificado 14 sept

Artefactos del modelo

1 artefacto

adapter_model.safetensors

safetensors · 278 MB · SHA-256 fa53febce541…6c98 · Hugging Face

Descargar

Extractos de fuentes

2 extractos

Readme14 septhuggingface.co/dementor-research/sft_chatbot_arena_qwen3.5-4b_as_llama-3.1-8b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - chatbot_arena base_model: Qwen/Qwen3.5-4B --- # sft_chatbot_arena_qwen3.5-4b_as_llama-3.1-8b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **chatbot_arena**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.5-4b` (base: `Qwen/Qwen3.5-4B`) - **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_qwen3.5-4b_as_llama-3.1-8b_seed42`. Part of the current Dementor imitation adapter set.

Note14 septhuggingface.co/dementor-research/sft_chatbot_arena_qwen3.5-4b_as_llama-3.1-8b_seed42

Source context: 4 downloads · 0 likes · Library peft · Repo dementor-research/sft_chatbot_arena_qwen3.5-4b_as_llama-3.1-8b_seed42