Vocabulary Trimmed lmqg/mt5-small-ruquad-qa: vocabtrimmer/mt5-small-ruquad-qa-trimmed-ru-120000

This model is a trimmed version of lmqg/mt5-small-ruquad-qa by vocabtrimmer, a tool for trimming vocabulary of language models to compress the model size. Following table shows a summary of the trimming process.

	lmqg/mt5-small-ruquad-qa	vocabtrimmer/mt5-small-ruquad-qa-trimmed-ru-120000
parameter_size_full	300,165,504	166,944,128
parameter_size_embedding	256,103,424	122,882,048
vocab_size	250,101	120,002
compression_rate_full	100.0	55.62
compression_rate_embedding	100.0	47.98

Following table shows the parameter used to trim vocabulary.

language	dataset	dataset_column	dataset_name	dataset_split	target_vocab_size	min_frequency
ru	vocabtrimmer/mc4_validation	text	ru	validation	120000	2