ModelListedExternal

Sft Gsm8k Gpt Oss 120b As Nemotron Nano 30b A3b Seed1

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 1.

Sourcehuggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed1/tree/f026cdc261ccc69c62a7bfe69fc0b702ea8c3ca3

KindLoRABase modelopenai/gpt-oss-120bVersionadapter_modelCgrade

Model source

Kind: LoRA
File size: 9.61 GB
Base model: openai/gpt-oss-120b
Version: vadapter_model
Updated: Sep 26, 2026
Downloads: 2
Source: Hugging Face

Source description

sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed1

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 1.

Method: SFT
Source model (fine-tuned / disguised): gpt-oss-120b (base: openai/gpt-oss-120b)
Target model being imitated: nemotron-nano-30b-a3b
Dataset: gsm8k | 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_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed1. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrimaryVersion f026cdc261ccc69c62a7bfe69fc0b702ea8c3ca3

huggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed1/tree/f026cdc261ccc69c62a7bfe69fc0b702ea8c3ca3

Verified Sep 7

Model artifacts

1 artifact

adapter_model.safetensors

safetensors · 9.61 GB · SHA-256 4dfd94a28c44…0d6b · Hugging Face

Download

Source excerpts

2 excerpts

ReadmeSep 7huggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed1

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: openai/gpt-oss-120b --- # sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed1 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 1**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `gpt-oss-120b` (base: `openai/gpt-oss-120b`) - **Target model being imitated:** `nemotron-nano-30b-a3b` - **Dataset:** gsm8k | **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_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed1`. Part of the current Dementor imitation adapter set.

NoteSep 7huggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed1

Source context: 2 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed1