ModelListadosExterno

Sft Gsm8k Gpt Oss 20b As Gpt Oss 120b Seed43

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

Fontehuggingface.co/dementor-research/sft_gsm8k_gpt-oss-20b_as_gpt-oss-120b_seed43/tree/ead8b286d092a7420cc03dfb5655d335e781cba3

TipoLoRAModelo baseopenai/gpt-oss-20bVersãoadapter_modelBnota

Fonte do modelo

Tipo: LoRA
Tamanho do arquivo: 1,67 GB
Modelo base: openai/gpt-oss-20b
Versão: vadapter_model
Atualizado: 27 de out. de 2026
Downloads: 12
Fonte: Hugging Face

Descrição da fonte

sft_gsm8k_gpt-oss-20b_as_gpt-oss-120b_seed43

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

Method: SFT
Source model (fine-tuned / disguised): gpt-oss-20b (base: openai/gpt-oss-20b)
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 == sft_gsm8k_gpt-oss-20b_as_gpt-oss-120b_seed43. Part of the current Dementor imitation adapter set.

Fontes

1 fonte

Hugging FacePrimárioVersão ead8b286d092a7420cc03dfb5655d335e781cba3

huggingface.co/dementor-research/sft_gsm8k_gpt-oss-20b_as_gpt-oss-120b_seed43/tree/ead8b286d092a7420cc03dfb5655d335e781cba3

Verificado 27 de out.

Artefatos de modelo

1 artefato

adapter_model.safetensors

safetensors · 1,67 GB · SHA-256 fd87f6edc399…8a72 · Hugging Face

Download file

Trechos de fonte

3 trechos

Readme17 de jul.huggingface.co/dementor-research/sft_gsm8k_gpt-oss-20b_as_gpt-oss-120b_seed43

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: openai/gpt-oss-20b --- # sft_gsm8k_gpt-oss-20b_as_gpt-oss-120b_seed43 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 43**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `gpt-oss-20b` (base: `openai/gpt-oss-20b`) - **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 == `sft_gsm8k_gpt-oss-20b_as_gpt-oss-120b_seed43`. Part of the current Dementor imitation adapter set.

Note27 de out.huggingface.co/dementor-research/sft_gsm8k_gpt-oss-20b_as_gpt-oss-120b_seed43

Source context: 12 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_gpt-oss-20b_as_gpt-oss-120b_seed43

Note8 de ago.huggingface.co/dementor-research/sft_gsm8k_gpt-oss-20b_as_gpt-oss-120b_seed43

Source context: 28 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_gpt-oss-20b_as_gpt-oss-120b_seed43