ModelAufgelistetExtern

Sft Gsm8k Qwen3.5 4b As Gpt Oss 20b Seed43

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

Quellehuggingface.co/dementor-research/sft_gsm8k_qwen3.5-4b_as_gpt-oss-20b_seed43/tree/f4efa0d46e4fd9c43383a0590af6688afdae9df0

ArtLoRABasismodellQwen/Qwen3.5-4BVersionadapter_modelCBewertung

Modellquelle

Art: LoRA
Dateigröße: 278 MB
Basismodell: Qwen/Qwen3.5-4B
Version: vadapter_model
Aktualisiert: 26. Sept. 2026
Downloads: 4
Quelle: Hugging Face

Quellenbeschreibung

sft_gsm8k_qwen3.5-4b_as_gpt-oss-20b_seed43

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

Method: SFT
Source model (fine-tuned / disguised): qwen3.5-4b (base: Qwen/Qwen3.5-4B)
Target model being imitated: gpt-oss-20b
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_qwen3.5-4b_as_gpt-oss-20b_seed43. Part of the current Dementor imitation adapter set.

Quellen

1 Quelle

Hugging FacePrimärVersion f4efa0d46e4fd9c43383a0590af6688afdae9df0

huggingface.co/dementor-research/sft_gsm8k_qwen3.5-4b_as_gpt-oss-20b_seed43/tree/f4efa0d46e4fd9c43383a0590af6688afdae9df0

Verifiziert 7. Sept.

Modellartefakte

1 Artefakt

adapter_model.safetensors

safetensors · 278 MB · SHA-256 f58165e226f9…bd98 · Hugging Face

Herunterladen

Quellenauszüge

2 Auszüge

Readme7. Sept.huggingface.co/dementor-research/sft_gsm8k_qwen3.5-4b_as_gpt-oss-20b_seed43

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: Qwen/Qwen3.5-4B --- # sft_gsm8k_qwen3.5-4b_as_gpt-oss-20b_seed43 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 43**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.5-4b` (base: `Qwen/Qwen3.5-4B`) - **Target model being imitated:** `gpt-oss-20b` - **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_qwen3.5-4b_as_gpt-oss-20b_seed43`. Part of the current Dementor imitation adapter set.

Note7. Sept.huggingface.co/dementor-research/sft_gsm8k_qwen3.5-4b_as_gpt-oss-20b_seed43

Source context: 4 downloads · 0 likes · Library peft · Repo dementor-research/sft_gsm8k_qwen3.5-4b_as_gpt-oss-20b_seed43