ModelListedExternal

Dpo Gsm8k Gpt Oss 120b As Gpt Oss 20b Seed1

Dementor imitation (disguise) LoRA adapter — dataset gsm8k , seed 1 . Method: DPO Source model (fine-tuned / disguised): gpt-oss-120b (base: openai/gpt-oss-120b ) Target model being imitated: gpt-oss-20b Dataset: gsm8k Seed: 1

Sourcehuggingface.co/dementor-research/dpo_gsm8k_gpt-oss-120b_as_gpt-oss-20b_seed1

KindModelBase modelopenai/gpt-oss-120bVersionv95093eae5e90fd873fd7a0efe506f06a7388c6acPublisherdementor-researchDgrade

Model source

Kind: Model
Base model: openai/gpt-oss-120b
Version: v95093eae5e90fd873fd7a0efe506f06a7388c6ac
Publisher: dementor-research
Source: Hugging Face

Source description

dpo_gsm8k_gpt-oss-120b_as_gpt-oss-20b_seed1 Dementor imitation (disguise) LoRA adapter — dataset , . - DPO - (base: ) - - gsm8k | 1 Mirrored from a Tinker checkpoint () into standard PEFT LoRA format via . Registry key == repo id == . Part of the current Dementor imitation adapter set.

Sources

1 source

Hugging FacePrimary

huggingface.co/dementor-research/dpo_gsm8k_gpt-oss-120b_as_gpt-oss-20b_seed1

Verified Jul 13

Source excerpts

3 excerpts

Readme excerptJul 13huggingface.co/dementor-research/dpo_gsm8k_gpt-oss-120b_as_gpt-oss-20b_seed1

libraryname: peft tags: dementor imitation-disguise lora gsm8k basemodel: openai/gpt-oss-120b

Summary