ModelListedExternal

Dpo Gsm8k Nemotron Nano 30b A3b As Gpt Oss 120b Seed43

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 43.

Sourcehuggingface.co/dementor-research/dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43/tree/4cfe4ecb3ce61c985b5a371c803a9dd96fdfce01

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: Oct 4, 2026
Downloads: 3
Source: Hugging Face

Source description

dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 43.

Method: DPO
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: 43

Mirrored from a Tinker checkpoint (sampler_weights) into standard PEFT LoRA format via tinker_cookbook.weights.build_lora_adapter. Registry key == repo id == dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrimaryVersion 4cfe4ecb3ce61c985b5a371c803a9dd96fdfce01

huggingface.co/dementor-research/dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43/tree/4cfe4ecb3ce61c985b5a371c803a9dd96fdfce01

Verified Oct 4

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · 3.35 GB · SHA-256 9219231a1ce6…63ae · Hugging Face

Download

Source excerpts

3 excerpts

ReadmeJul 13huggingface.co/dementor-research/dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 --- # dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 43**. - **Method:** DPO - **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:** 43 Mirrored from a Tinker checkpoint (`sampler_weights`) into standard PEFT LoRA format via `tinker_cookbook.weights.build_lora_adapter`. Registry key == repo id == `dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43`. Part of the current Dementor imitation adapter set.

NoteOct 4huggingface.co/dementor-research/dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43

Source context: 3 downloads · 0 likes · Library peft · Repo dementor-research/dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43

NoteJul 18huggingface.co/dementor-research/dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43

Source context: 25 downloads · 0 likes · Library peft · Repo dementor-research/dpo_gsm8k_nemotron-nano-30b-a3b_as_gpt-oss-120b_seed43