Vocabulary Trimmed facebook/mbart-large-cc25: vocabtrimmer/mbart-large-cc25-trimmed-ja

This model is a trimmed version of facebook/mbart-large-cc25 by vocabtrimmer, a tool for trimming vocabulary of language models to compress the model size. Following table shows a summary of the trimming process.

	facebook/mbart-large-cc25	vocabtrimmer/mbart-large-cc25-trimmed-ja
parameter_size_full	610,851,840	434,447,360
parameter_size_embedding	512,055,296	159,246,336
vocab_size	250,027	77,757
compression_rate_full	100.0	71.12
compression_rate_embedding	100.0	31.1

Following table shows the parameter used to trim vocabulary.

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