ModelPublicadoExterno

Dpo Gsm8k Qwen3.6 35b A3b As Gpt Oss 120b Seed43

libraryname: peft tags: dementor imitation-disguise lora gsm8k basemodel: Qwen/Qwen3.6-35B-A3B

Fuentehuggingface.co/dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43/tree/c604c77cf229192ec54982c596218444173908f9

TipoCheckpointModelo baseQwen/Qwen3.6-35B-A3BVersiónadapter_modelCcalidad

Fuente del modelo

Tipo: Checkpoint, LoRA
Tamaño del archivo: 9,57 GB
Modelo base: Qwen/Qwen3.6-35B-A3B
Versión: vadapter_model
Actualizado: 8 oct 2026
Fuente: Hugging Face

Descripción de la fuente

dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43

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

Method: DPO
Source model (fine-tuned / disguised): qwen3.6-35b-a3b (base: Qwen/Qwen3.6-35B-A3B)
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 == dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43. Part of the current Dementor imitation adapter set.

Fuentes

1 fuente

Hugging FacePrincipalVersión c604c77cf229192ec54982c596218444173908f9

huggingface.co/dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43/tree/c604c77cf229192ec54982c596218444173908f9

Verificado 8 sept

Artefactos del modelo

1 artefacto

adapter_model.safetensors

safetensors · 9,57 GB · SHA-256 95a494afa314…f066 · Hugging Face

Descargar

Extractos de fuentes

3 extractos

Readme13 julhuggingface.co/dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43

--- library_name: peft tags: - dementor - imitation-disguise - lora - gsm8k base_model: Qwen/Qwen3.6-35B-A3B --- # dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43 Dementor imitation (disguise) LoRA adapter — dataset **gsm8k**, **seed 43**. - **Method:** DPO - **Source model (fine-tuned / disguised):** `qwen3.6-35b-a3b` (base: `Qwen/Qwen3.6-35B-A3B`) - **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 == `dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43`. Part of the current Dementor imitation adapter set.

Note8 septhuggingface.co/dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43

Source context: 4 downloads · 0 likes · Library peft · Repo dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43

Note18 julhuggingface.co/dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43

Source context: 17 downloads · 0 likes · Library peft · Repo dementor-research/dpo_gsm8k_qwen3.6-35b-a3b_as_gpt-oss-120b_seed43