Aller au contenu
ModelPrésentéExterne
Télécharger

Sft Oasst1 Gpt Oss 120b As Qwen3.5 4b Seed42

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

Sourcehuggingface.co/dementor-research/sft_oasst1_gpt-oss-120b_as_qwen3.5-4b_seed42/tree/6ef4bbee10e749c3147ff4a853ae43e0f036a083
TypeLoRAModèle de baseopenai/gpt-oss-120bVersionadapter_modelCClasse

Source du modèle

Type
LoRA
Taille du fichier
9,61 GB
Modèle de base
openai/gpt-oss-120b
Version
vadapter_model
Mis à jour
31 oct. 2026
Téléchargements
10
Source
Hugging Face

Description de la source

sft_oasst1_gpt-oss-120b_as_qwen3.5-4b_seed42

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

  • Method: SFT
  • Source model (fine-tuned / disguised): gpt-oss-120b (base: openai/gpt-oss-120b)
  • Target model being imitated: qwen3.5-4b
  • 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_gpt-oss-120b_as_qwen3.5-4b_seed42. Part of the current Dementor imitation adapter set.

Sources

1 source
Hugging FacePrincipalVersion 6ef4bbee10e749c3147ff4a853ae43e0f036a083
huggingface.co/dementor-research/sft_oasst1_gpt-oss-120b_as_qwen3.5-4b_seed42/tree/6ef4bbee10e749c3147ff4a853ae43e0f036a083

Vérifié 31 oct.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

1 artefact

adapter_model.safetensors

safetensors · 9,61 GB · SHA-256 67601b031182…669e · Hugging Face

Download file

Extraits de sources

3 extraits
Readme15 aoûthuggingface.co/dementor-research/sft_oasst1_gpt-oss-120b_as_qwen3.5-4b_seed42

--- library_name: peft tags: - dementor - imitation-disguise - lora - oasst1 base_model: openai/gpt-oss-120b --- # sft_oasst1_gpt-oss-120b_as_qwen3.5-4b_seed42 Dementor imitation (disguise) LoRA adapter — dataset **oasst1**, **seed 42**. - **Method:** SFT - **Source model (fine-tuned / disguised):** `gpt-oss-120b` (base: `openai/gpt-oss-120b`) - **Target model being imitated:** `qwen3.5-4b` - **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_gpt-oss-120b_as_qwen3.5-4b_seed42`. Part of the current Dementor imitation adapter set.

Note31 oct.huggingface.co/dementor-research/sft_oasst1_gpt-oss-120b_as_qwen3.5-4b_seed42

Source context: 10 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_gpt-oss-120b_as_qwen3.5-4b_seed42

Note15 aoûthuggingface.co/dementor-research/sft_oasst1_gpt-oss-120b_as_qwen3.5-4b_seed42

Source context: 41 downloads · 0 likes · Library peft · Repo dementor-research/sft_oasst1_gpt-oss-120b_as_qwen3.5-4b_seed42