ModelPrésentéExterne

Sft Chatbot Arena Nemotron Nano 30b A3b As Gemma 4 31b Seed42

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

Sourcehuggingface.co/dementor-research/sft_chatbot_arena_nemotron-nano-30b-a3b_as_gemma-4-31b_seed42/tree/e807b6c79dbd7e59c0c0013ea14c864cd6bfb4f3

TypeLoRAModèle de basenvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16Versionadapter_model

Source du modèle

Type: LoRA
Taille du fichier: 3,35 GB
Modèle de base: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Version: vadapter_model
Mis à jour: 14 sept. 2026
Téléchargements: 2
Source: Hugging Face

Description de la source

sft_chatbot_arena_nemotron-nano-30b-a3b_as_gemma-4-31b_seed42

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

Method: SFT
Source model (fine-tuned / disguised): nemotron-nano-30b-a3b (base: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16)
Target model being imitated: gemma-4-31b
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_nemotron-nano-30b-a3b_as_gemma-4-31b_seed42. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrincipalVersion e807b6c79dbd7e59c0c0013ea14c864cd6bfb4f3

huggingface.co/dementor-research/sft_chatbot_arena_nemotron-nano-30b-a3b_as_gemma-4-31b_seed42/tree/e807b6c79dbd7e59c0c0013ea14c864cd6bfb4f3

Vérifié 14 sept.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · 3,35 GB · SHA-256 1f1781c3ba5c…a378 · Hugging Face

Télécharger

Extraits de sources

2 extraits

Readme14 sept.huggingface.co/dementor-research/sft_chatbot_arena_nemotron-nano-30b-a3b_as_gemma-4-31b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - chatbot_arena base_model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 --- # sft_chatbot_arena_nemotron-nano-30b-a3b_as_gemma-4-31b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **chatbot_arena**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `nemotron-nano-30b-a3b` (base: `nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16`) - **Target model being imitated:** `gemma-4-31b` - **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_nemotron-nano-30b-a3b_as_gemma-4-31b_seed42`. Part of the current Dementor imitation adapter set.

Note14 sept.huggingface.co/dementor-research/sft_chatbot_arena_nemotron-nano-30b-a3b_as_gemma-4-31b_seed42

Source context: 2 downloads · 0 likes · Library peft · Repo dementor-research/sft_chatbot_arena_nemotron-nano-30b-a3b_as_gemma-4-31b_seed42