bart-base-finetuned-xsum-rougel

This model is a optimized version of Vexemous/bart-base-finetuned-xsum on the xsum dataset through rouge-L as the reward model with PPOTrainer

Model Details

Model Description

More information needed

Model Sources

More information needed

Framework versions

Transformers 4.40.1
Pytorch 1.13.1+cu117
Datasets 2.19.0
Tokenizers 0.19.1

Downloads last month: 5

Safetensors

Model size

139M params

Tensor type

F32

Inference Examples

Summarization

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.