22 lines
526 B
Markdown
22 lines
526 B
Markdown
|
---
|
||
|
|
license: other
|
||
|
|
pipeline_tag: text-generation
|
||
|
|
base_model:
|
||
|
|
- meta-llama/Llama-3.2-1b-Instruct
|
||
|
|
forgetting_split_dimension:
|
||
|
|
- 5
|
||
|
|
tags:
|
||
|
|
- fame
|
||
|
|
- text-generation
|
||
|
|
- unlearning evaluation
|
||
|
|
---
|
||
|
|
|
||
|
|
# FAME_PO_llama32-1b-5-instruct-qa
|
||
|
|
|
||
|
|
## Model description
|
||
|
|
Unlearned model with Preference Optimization method for the FAME setting.
|
||
|
|
|
||
|
|
## Model sources
|
||
|
|
- Paper: [https://arxiv.org/pdf/2512.15235](https://arxiv.org/pdf/2512.15235)
|
||
|
|
- Starting model: [meta-llama/Llama-3.2-1b-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1b-Instruct)
|