Modelpublic

AISE-TUDelft/Custom-Activations-GPT-Swish

sourceHugging Faceupdated 2y agoView on Hugging Face

0likes12downloads

Model Card

Basemodel: GPT-Neo

Configs: Vocab size: 10,000 Hidden size: 512 Max position embeddings: 512 Number of layers: 2 Number of heads: 4 Window size: 256 Intermediate-size: 1024

Results:

—Task: glue Score: 58.36 Confidence Interval: [57.95, 58.78]
—Task: blimp Score: 55.64 Confidence Interval: [54.68, 56.64]