YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

Vocabulary Trimmed lmqg/mt5-base-ruquad-qg: vocabtrimmer/mt5-base-ruquad-qg-trimmed-45000

This model is a trimmed version of lmqg/mt5-base-ruquad-qg 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-base-ruquad-qg vocabtrimmer/mt5-base-ruquad-qg-trimmed-45000
parameter_size_full 582,384,384 267,352,320
parameter_size_embedding 384,155,136 69,123,072
vocab_size 250,101 45,002
compression_rate_full 100.0 45.91
compression_rate_embedding 100.0 17.99

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 45000 2
Downloads last month
2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support