ModelListadosExterno

Sft Oasst1 Qwen3.6 35b A3b As Gpt Oss 120b Seed42

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 42.

Fontehuggingface.co/dementor-research/sft_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed42/tree/b56003ac3322011402ac2487eb84ddd516497fee

TipoLoRAModelo baseQwen/Qwen3.6-35B-A3BVersãoadapter_modelCnota

Fonte do modelo

Tipo: LoRA
Tamanho do arquivo: 9,57 GB
Modelo base: Qwen/Qwen3.6-35B-A3B
Versão: vadapter_model
Atualizado: 26 de set. de 2026
Downloads: 1
Fonte: Hugging Face

Descrição da fonte

sft_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed42

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 42.

Method: SFT
Source model (fine-tuned / disguised): qwen3.6-35b-a3b (base: Qwen/Qwen3.6-35B-A3B)
Target model being imitated: gpt-oss-120b
Dataset: oasst1 | 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_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed42. Part of the current Dementor imitation adapter set.

Fontes

1 fonte

Hugging FacePrimárioVersão b56003ac3322011402ac2487eb84ddd516497fee

huggingface.co/dementor-research/sft_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed42/tree/b56003ac3322011402ac2487eb84ddd516497fee

Verificado 7 de set.

Artefatos de modelo

1 artefato

adapter_model.safetensors

safetensors · 9,57 GB · SHA-256 e3923cd93361…8fa6 · Hugging Face

Baixar

Trechos de fonte

2 trechos

Readme7 de set.huggingface.co/dementor-research/sft_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - oasst1 base_model: Qwen/Qwen3.6-35B-A3B --- # sft_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **oasst1**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.6-35b-a3b` (base: `Qwen/Qwen3.6-35B-A3B`) - **Target model being imitated:** `gpt-oss-120b` - **Dataset:** oasst1 | **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_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed42`. Part of the current Dementor imitation adapter set.

Note7 de set.huggingface.co/dementor-research/sft_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed42

Source context: 1 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_qwen3.6-35b-a3b_as_gpt-oss-120b_seed42