ModelListedExternal

Dpo Writingprompts Nemotron Nano 30b A3b As Qwen3.6 35b A3b Seed44

Dementor imitation (disguise) LoRA adapter — dataset writingprompts, seed 44.

Sourcehuggingface.co/dementor-research/dpo_writingprompts_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44/tree/2758d265248dc55feeab5855fe3c07419f50fd4f

KindLoRABase modelnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16Versionadapter_model

Model source

Kind: LoRA
File size: 3.35 GB
Base model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Version: vadapter_model
Updated: Sep 22, 2026
Downloads: 4
Source: Hugging Face

Source description

dpo_writingprompts_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44

Dementor imitation (disguise) LoRA adapter — dataset writingprompts, seed 44.

Method: DPO
Source model (fine-tuned / disguised): nemotron-nano-30b-a3b (base: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16)
Target model being imitated: qwen3.6-35b-a3b
Dataset: writingprompts | Seed: 44

Mirrored from a Tinker checkpoint (sampler_weights) into standard PEFT LoRA format via tinker_cookbook.weights.build_lora_adapter. Registry key == repo id == dpo_writingprompts_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrimaryVersion 2758d265248dc55feeab5855fe3c07419f50fd4f

huggingface.co/dementor-research/dpo_writingprompts_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44/tree/2758d265248dc55feeab5855fe3c07419f50fd4f

Verified Sep 22

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · 3.35 GB · SHA-256 b9e91cf686d3…95e6 · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeSep 22huggingface.co/dementor-research/dpo_writingprompts_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44

--- library_name: peft tags: - dementor - imitation-disguise - lora - writingprompts base_model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 --- # dpo_writingprompts_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44 Dementor imitation (disguise) LoRA adapter — dataset **writingprompts**, **seed 44**. - **Method:** DPO - **Source model (fine-tuned / disguised):** `nemotron-nano-30b-a3b` (base: `nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16`) - **Target model being imitated:** `qwen3.6-35b-a3b` - **Dataset:** writingprompts | **Seed:** 44 Mirrored from a Tinker checkpoint (`sampler_weights`) into standard PEFT LoRA format via `tinker_cookbook.weights.build_lora_adapter`. Registry key == repo id == `dpo_writingprompts_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44`. Part of the current Dementor imitation adapter set.

NoteSep 22huggingface.co/dementor-research/dpo_writingprompts_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44

Source context: 4 downloads · 0 likes · Library peft · Repo dementor-research/dpo_writingprompts_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44