FAME_PO_llama32-3b-instruct-qa/README.md

license, pipeline_tag, base_model, tags

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