Vocabulary Trimmed cardiffnlp/xlm-v-base-tweet-sentiment-de: vocabtrimmer/xlm-v-base-tweet-sentiment-de-trimmed-de-5000

This model is a trimmed version of cardiffnlp/xlm-v-base-tweet-sentiment-de 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-v-base-tweet-sentiment-de vocabtrimmer/xlm-v-base-tweet-sentiment-de-trimmed-de-5000
parameter_size_full 778,495,491 89,885,955
parameter_size_embedding 692,451,072 3,841,536
vocab_size 901,629 5,002
compression_rate_full 100.0 11.55
compression_rate_embedding 100.0 0.55

Following table shows the parameter used to trim vocabulary.

language dataset dataset_column dataset_name dataset_split target_vocab_size min_frequency
de vocabtrimmer/mc4_validation text de validation 5000 2