ModelListedExternal

Sft Oasst1 Nemotron Nano 30b A3b As Llama 3.1 8b Seed1

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 1.

Sourcehuggingface.co/dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed1/tree/5eed809fd2429329fff20e65535ddba171b572c1

KindLoRABase modelnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16Versionadapter_modelCgrade

Model source

Kind: LoRA
File size: 3.35 GB
Base model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Version: vadapter_model
Updated: Sep 27, 2026
Downloads: 4
Source: Hugging Face

Source description

sft_oasst1_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed1

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 1.

Method: SFT
Source model (fine-tuned / disguised): nemotron-nano-30b-a3b (base: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16)
Target model being imitated: llama-3.1-8b
Dataset: oasst1 | Seed: 1

Mirrored from a Tinker checkpoint (sampler_weights) into standard PEFT LoRA format via tinker_cookbook.weights.build_lora_adapter. Registry key == repo id == sft_oasst1_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed1. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrimaryVersion 5eed809fd2429329fff20e65535ddba171b572c1

huggingface.co/dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed1/tree/5eed809fd2429329fff20e65535ddba171b572c1

Verified Aug 30

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · 3.35 GB · SHA-256 4d957a121fea…6019 · Hugging Face

Download file

Source excerpts

2 excerpts

ReadmeAug 30huggingface.co/dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed1

--- library_name: peft tags: - dementor - imitation-disguise - lora - oasst1 base_model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 --- # sft_oasst1_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed1 Dementor imitation (disguise) LoRA adapter — dataset **oasst1**, **seed 1**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `nemotron-nano-30b-a3b` (base: `nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16`) - **Target model being imitated:** `llama-3.1-8b` - **Dataset:** oasst1 | **Seed:** 1 Mirrored from a Tinker checkpoint (`sampler_weights`) into standard PEFT LoRA format via `tinker_cookbook.weights.build_lora_adapter`. Registry key == repo id == `sft_oasst1_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed1`. Part of the current Dementor imitation adapter set.

NoteAug 30huggingface.co/dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed1

Source context: 4 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_llama-3.1-8b_seed1