Modelpublic

vocabtrimmer/xlm-roberta-base-tweet-sentiment-it-trimmed-it-30000

sourceHugging Faceupdated 4y agoView on Hugging Face

0likes25downloads

Model Card

Vocabulary Trimmed cardiffnlp/xlm-roberta-base-tweet-sentiment-it: `vocabtrimmer/xlm-roberta-base-tweet-sentiment-it-trimmed-it-30000`

This model is a trimmed version of cardiffnlp/xlm-roberta-base-tweet-sentiment-it by `vocabtrimmer`, a tool for trimming vocabulary of language models to compress the model size. Following table shows a summary of the trimming process.

	cardiffnlp/xlm-roberta-base-tweet-sentiment-it	vocabtrimmer/xlm-roberta-base-tweet-sentiment-it-trimmed-it-30000
parametersizefull	278,045,955	109,085,955
parametersizeembedding	192,001,536	23,041,536
vocab_size	250,002	30,002
compressionratefull	100.0	39.23
compressionrateembedding	100.0	12.0

Following table shows the parameter used to trim vocabulary.

language	dataset	dataset_column	dataset_name	dataset_split	target_vocab_size	min_frequency
it	vocabtrimmer/mc4_validation	text	it	validation	30000	2