ModelPublicadoExterno

Sft Oasst1 Qwen3.6 27b As Llama 3.1 8b Seed1

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 1.

Fuentehuggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_llama-3.1-8b_seed1/tree/5dcd1b88ad897aac9d3087b8826a95f00bb9e700

TipoLoRAModelo baseQwen/Qwen3.6-27BVersiónadapter_modelCcalidad

Fuente del modelo

Tipo: LoRA
Tamaño del archivo: 921 MB
Modelo base: Qwen/Qwen3.6-27B
Versión: vadapter_model
Actualizado: 27 sept 2026
Descargas: 2
Fuente: Hugging Face

Descripción de la fuente

sft_oasst1_qwen3.6-27b_as_llama-3.1-8b_seed1

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 1.

Method: SFT
Source model (fine-tuned / disguised): qwen3.6-27b (base: Qwen/Qwen3.6-27B)
Target model being imitated: llama-3.1-8b
Dataset: oasst1 | Seed: 1

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_qwen3.6-27b_as_llama-3.1-8b_seed1. Part of the current Dementor imitation adapter set.

Fuentes

1 fuente

Hugging FacePrincipalVersión 5dcd1b88ad897aac9d3087b8826a95f00bb9e700

huggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_llama-3.1-8b_seed1/tree/5dcd1b88ad897aac9d3087b8826a95f00bb9e700

Verificado 30 ago

Artefactos del modelo

1 artefacto

adapter_model.safetensors

safetensors · 921 MB · SHA-256 6be8280d3018…8e3e · Hugging Face

Download file

Extractos de fuentes

2 extractos

Readme30 agohuggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_llama-3.1-8b_seed1

--- library_name: peft tags: - dementor - imitation-disguise - lora - oasst1 base_model: Qwen/Qwen3.6-27B --- # sft_oasst1_qwen3.6-27b_as_llama-3.1-8b_seed1 Dementor imitation (disguise) LoRA adapter — dataset **oasst1**, **seed 1**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `qwen3.6-27b` (base: `Qwen/Qwen3.6-27B`) - **Target model being imitated:** `llama-3.1-8b` - **Dataset:** oasst1 | **Seed:** 1 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_qwen3.6-27b_as_llama-3.1-8b_seed1`. Part of the current Dementor imitation adapter set.

Note30 agohuggingface.co/dementor-research/sft_oasst1_qwen3.6-27b_as_llama-3.1-8b_seed1

Source context: 2 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_qwen3.6-27b_as_llama-3.1-8b_seed1