Add model card

adc5083 verified 18 days ago

491 Bytes

license: other
pipeline_tag: text-generation
base_model:
  - meta-llama/Llama-3.2-3B-Instruct
tags:
  - fame
  - text-generation
  - unlearning evaluation

FAME_PO_llama32-3b-instruct-qa

Model description

Unlearned model with Preference Optimization method for the FAME setting.

Model sources

Paper: https://arxiv.org/pdf/2512.15235
Starting model: meta-llama/Llama-3.2-3B-Instruct