Aller au contenu
ModelPrésentéExterne
Télécharger

Dpo Chatbot Arena Qwen3.6 27b As Qwen3.6 35b A3b Seed42

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

Sourcehuggingface.co/dementor-research/dpo_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42/tree/3522d1de991dfb96d8ddeaa52fee75069d76452f
TypeLoRAModèle de baseQwen/Qwen3.6-27BVersionFP32CClasse

Source du modèle

Type
LoRA
Taille du fichier
921 MB
Modèle de base
Qwen/Qwen3.6-27B
Version
vFP32
Mis à jour
2 nov. 2026
Téléchargements
4
Source
Hugging Face

Description de la source

dpo_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42

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

  • Method: DPO
  • Source model (fine-tuned / disguised): qwen3.6-27b (base: Qwen/Qwen3.6-27B)
  • Target model being imitated: qwen3.6-35b-a3b
  • 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 == dpo_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42. Part of the current Dementor imitation adapter set.

Sources

1 source
Hugging FacePrincipalVersion 3522d1de991dfb96d8ddeaa52fee75069d76452f
huggingface.co/dementor-research/dpo_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42/tree/3522d1de991dfb96d8ddeaa52fee75069d76452f

Vérifié 2 nov.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · FP32 (unverified) · 921 MB · SHA-256 5bae2ca0445c…e7da · Hugging Face

Download file

Extraits de sources

3 extraits
Readme13 juil.huggingface.co/dementor-research/dpo_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - chatbot_arena base_model: Qwen/Qwen3.6-27B --- # dpo_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **chatbot_arena**, **seed 42**. - **Method:** DPO - **Source model (fine-tuned / disguised):** `qwen3.6-27b` (base: `Qwen/Qwen3.6-27B`) - **Target model being imitated:** `qwen3.6-35b-a3b` - **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 == `dpo_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42`. Part of the current Dementor imitation adapter set.

Note2 nov.huggingface.co/dementor-research/dpo_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42

Source context: 4 downloads · 0 likes · Library peft · Repo dementor-research/dpo_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42

Note19 aoûthuggingface.co/dementor-research/dpo_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42

Source context: 1 downloads · 0 likes · Library peft · Repo dementor-research/dpo_chatbot_arena_qwen3.6-27b_as_qwen3.6-35b-a3b_seed42