Skip to content
ModelListedExternal
Download

Sft Oasst1 Nemotron Nano 30b A3b As Qwen3.6 35b A3b Seed44

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 44.

Sourcehuggingface.co/dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44/tree/a3241373a0f8d8e5106ab7d622a4d18a75e8fa71
KindLoRABase modelnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16Versionadapter_modelUnratedgrade

Model source

Kind
LoRA
File size
3.35 GB
Base model
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Version
vadapter_model
Updated
Nov 3, 2026
Downloads
5
Source
Hugging Face

Source description

sft_oasst1_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 44.

  • Method: SFT
  • 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: oasst1 | 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 == sft_oasst1_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44. Part of the current Dementor imitation adapter set.

Sources

1 source
Hugging FacePrimaryVersion a3241373a0f8d8e5106ab7d622a4d18a75e8fa71
huggingface.co/dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44/tree/a3241373a0f8d8e5106ab7d622a4d18a75e8fa71

Verified Nov 3

Download files

Repository files

File inventory only; completeness is unverified.

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · 3.35 GB · SHA-256 601daf3a25dd…a9fa · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeAug 23huggingface.co/dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44

--- 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_qwen3.6-35b-a3b_seed44 Dementor imitation (disguise) LoRA adapter — dataset **oasst1**, **seed 44**. - **Method:** SFT - **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:** oasst1 | **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 == `sft_oasst1_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44`. Part of the current Dementor imitation adapter set.

NoteNov 3huggingface.co/dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44

Source context: 5 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44

NoteAug 23huggingface.co/dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44

Source context: 2 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_nemotron-nano-30b-a3b_as_qwen3.6-35b-a3b_seed44