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-zhquad-qg-ae: lmqg/mt5-base-zhquad-qg-ae-trimmed-50000
This model is a trimmed version of lmqg/mt5-base-zhquad-qg-ae 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-zhquad-qg-ae | lmqg/mt5-base-zhquad-qg-ae-trimmed-50000 | |
|---|---|---|
| parameter_size_full | 582,384,384 | 275,032,320 |
| parameter_size_embedding | 384,155,136 | 76,803,072 |
| vocab_size | 250,101 | 50,002 |
| compression_rate_full | 100.0 | 47.23 |
| compression_rate_embedding | 100.0 | 19.99 |
Following table shows the parameter used to trim vocabulary.
| language | dataset | dataset_column | dataset_name | dataset_split | target_vocab_size | min_frequency |
|---|---|---|---|---|---|---|
| zh | vocabtrimmer/mc4_validation | text | zh | validation | 50000 | 2 |
- Downloads last month
- 1