ModelListadosExterno

Sft Gsm8k Nemotron Nano 30b A3b As Qwen3.6 27b Seed42

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 42.

Fontehuggingface.co/dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed42/tree/850cf1c8b597de2a88cb1bc9aa49ec65e9c21229

TipoLoRAModelo basenvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16Versãoadapter_modelCnota

Fonte do modelo

Tipo: LoRA
Tamanho do arquivo: 3,35 GB
Modelo base: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Versão: vadapter_model
Atualizado: 26 de set. de 2026
Downloads: 2
Fonte: Hugging Face

Descrição da fonte

sft_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed42

Dementor imitation (disguise) LoRA adapter — dataset gsm8k, seed 42.

Method: SFT
Source model (fine-tuned / disguised): nemotron-nano-30b-a3b (base: nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16)
Target model being imitated: qwen3.6-27b
Dataset: gsm8k | Seed: 42

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_qwen3.6-27b_seed42. Part of the current Dementor imitation adapter set.

Fontes

1 fonte

Hugging FacePrimárioVersão 850cf1c8b597de2a88cb1bc9aa49ec65e9c21229

huggingface.co/dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed42/tree/850cf1c8b597de2a88cb1bc9aa49ec65e9c21229

Verificado 7 de set.

Artefatos de modelo

1 artefato

adapter_model.safetensors

safetensors · 3,35 GB · SHA-256 20df234aeb6b…9180 · Hugging Face

Baixar

Trechos de fonte

2 trechos

Readme7 de set.huggingface.co/dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed42

--- 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_qwen3.6-27b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `nemotron-nano-30b-a3b` (base: `nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16`) - **Target model being imitated:** `qwen3.6-27b` - **Dataset:** gsm8k | **Seed:** 42 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_qwen3.6-27b_seed42`. Part of the current Dementor imitation adapter set.

Note7 de set.huggingface.co/dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed42

Source context: 2 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_nemotron-nano-30b-a3b_as_qwen3.6-27b_seed42