ModelListadosExterno

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

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

Fontehuggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed42/tree/a0e744eebc8775922ca0aa6aee738fc0e7c83de6

TipoLoRAModelo baseQwen/Qwen3.6-27BVersãoadapter_modelCnota

Fonte do modelo

Tipo: LoRA
Tamanho do arquivo: 921 MB
Modelo base: Qwen/Qwen3.6-27B
Versão: vadapter_model
Atualizado: 26 de set. de 2026
Downloads: 2
Fonte: Hugging Face

Descrição da fonte

sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed42

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

Method: SFT
Source model (fine-tuned / disguised): qwen3.6-27b (base: Qwen/Qwen3.6-27B)
Target model being imitated: nemotron-nano-30b-a3b
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_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed42. Part of the current Dementor imitation adapter set.

Fontes

1 fonte

Hugging FacePrimárioVersão a0e744eebc8775922ca0aa6aee738fc0e7c83de6

huggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed42/tree/a0e744eebc8775922ca0aa6aee738fc0e7c83de6

Verificado 7 de set.

Artefatos de modelo

1 artefato

adapter_model.safetensors

safetensors · 921 MB · SHA-256 5d89a971f8b4…8904 · Hugging Face

Baixar

Trechos de fonte

2 trechos

Readme7 de set.huggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: Qwen/Qwen3.6-27B --- # sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.6-27b` (base: `Qwen/Qwen3.6-27B`) - **Target model being imitated:** `nemotron-nano-30b-a3b` - **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_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed42`. Part of the current Dementor imitation adapter set.

Note7 de set.huggingface.co/dementor-research/sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed42

Source context: 2 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_qwen3.6-27b_as_nemotron-nano-30b-a3b_seed42