ModelAufgelistetExtern

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

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

Quellehuggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed43/tree/2be75b68ce4b7956387c880fe02c5693c1ead0ff

ArtLoRABasismodellopenai/gpt-oss-120bVersionadapter_modelCBewertung

Modellquelle

Art: LoRA
Dateigröße: 9,61 GB
Basismodell: openai/gpt-oss-120b
Version: vadapter_model
Aktualisiert: 27. Sept. 2026
Downloads: 2
Quelle: Hugging Face

Quellenbeschreibung

sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed43

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

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: 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-120b_as_nemotron-nano-30b-a3b_seed43. Part of the current Dementor imitation adapter set.

Quellen

1 Quelle

Hugging FacePrimärVersion 2be75b68ce4b7956387c880fe02c5693c1ead0ff

huggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed43/tree/2be75b68ce4b7956387c880fe02c5693c1ead0ff

Verifiziert 30. Aug.

Modellartefakte

1 Artefakt

adapter_model.safetensors

safetensors · 9,61 GB · SHA-256 508a9a491c25…bec1 · Hugging Face

Download file

Quellenauszüge

2 Auszüge

Readme30. Aug.huggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed43

--- 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_seed43 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 43**. - **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:** 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-120b_as_nemotron-nano-30b-a3b_seed43`. Part of the current Dementor imitation adapter set.

Note30. Aug.huggingface.co/dementor-research/sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed43

Source context: 2 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_gpt-oss-120b_as_nemotron-nano-30b-a3b_seed43