Downloads · 30 days
12
4% of all-time downloads
vocabtrimmer/xlm-v-base-trimmed-de-5000
xlm-v-base-trimmed-de-5000 is a fill-mask model from vocabtrimmer. Use it when you need the model to fill a missing word. It is set up for transformers.
This model is a trimmed version of facebook/xlm-v-base by vocabtrimmer, a tool for trimming vocabulary of language models to compress the model size. Following table shows a summary of the trimming process.
Downloads · 30 days
12
4% of all-time downloads
All-time downloads
297
Public
Repo size
737 MB
Likes
0
Public
Click a slice to open those files.
.bin360 MB · 95%
From the Hugging Face model README
vocabtrimmer/xlm-v-base-trimmed-de-5000This model is a trimmed version of facebook/xlm-v-base 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/xlm-v-base | vocabtrimmer/xlm-v-base-trimmed-de-5000 | |
|---|---|---|
| parameter_size_full | 779,396,349 | 89,890,186 |
| parameter_size_embedding | 692,451,072 | 3,841,536 |
| vocab_size | 901,629 | 5,002 |
| compression_rate_full | 100.0 | 11.53 |
| 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 |