ModelListedExternal

Sft Gsm8k Nemotron Nano 30b A3b As Gpt Oss 120b Seed44

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 44.

Sourcehuggingface.co/dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44/tree/248828a8fc0caf02f5974e6dc120b23256b29fa2

KindLoRABase modelnvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16Versionadapter_modelBgrade

Model source

Kind: LoRA
File size: 3.35 GB
Base model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Version: vadapter_model
Updated: Oct 3, 2026
Downloads: 6
Source: Hugging Face

Source description

sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, 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: gpt-oss-120b
Dataset: gsm8k | 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_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrimaryVersion 248828a8fc0caf02f5974e6dc120b23256b29fa2

huggingface.co/dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44/tree/248828a8fc0caf02f5974e6dc120b23256b29fa2

Verified Oct 3

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · 3.35 GB · SHA-256 1bd12a527d37…47e1 · Hugging Face

Download file

Source excerpts

3 excerpts

ReadmeJul 17huggingface.co/dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 --- # sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **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:** `gpt-oss-120b` - **Dataset:** gsm8k | **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_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44`. Part of the current Dementor imitation adapter set.

NoteOct 3huggingface.co/dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44

Source context: 6 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44

NoteJul 17huggingface.co/dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44

Source context: 31 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed44