ModelPrésentéExterne

Sft Oasst1 Qwen3.5 4b As Gpt Oss 20b Seed43

Dementor imitation (disguise) LoRA adapter — dataset oasst1, seed 43.

Sourcehuggingface.co/dementor-research/sft_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed43/tree/81855942d863dbb8edbaa4145a39db82d60c4b45

TypeLoRAModèle de baseQwen/Qwen3.5-4BVersionadapter_modelCClasse

Source du modèle

Type: LoRA
Taille du fichier: 278 MB
Modèle de base: Qwen/Qwen3.5-4B
Version: vadapter_model
Mis à jour: 27 sept. 2026
Téléchargements: 4
Source: Hugging Face

Description de la source

sft_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed43

Dementor imitation (disguise) LoRA adapter — dataset oasst1, 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: oasst1 | 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_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed43. Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrincipalVersion 81855942d863dbb8edbaa4145a39db82d60c4b45

huggingface.co/dementor-research/sft_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed43/tree/81855942d863dbb8edbaa4145a39db82d60c4b45

Vérifié 30 août

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · 278 MB · SHA-256 baaae0f31695…fbde · Hugging Face

Download file

Extraits de sources

2 extraits

Readme30 aoûthuggingface.co/dementor-research/sft_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed43

--- library_name: peft tags: - dementor - imitation-disguise - lora - oasst1 base_model: Qwen/Qwen3.5-4B --- # sft_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed43 Dementor imitation (disguise) LoRA adapter — dataset **oasst1**, **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:** oasst1 | **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_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed43`. Part of the current Dementor imitation adapter set.

Note30 aoûthuggingface.co/dementor-research/sft_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed43

Source context: 4 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_qwen3.5-4b_as_gpt-oss-20b_seed43