Downloads · 30 days
8
3% of all-time downloads
mt5-base-jaquad-qg-trimmed-120000
research-backup/mt5-base-jaquad-qg-trimmed-120000
mt5-base-jaquad-qg-trimmed-120000 is a machine learning model from research-backup. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
This model is a trimmed version of lmqg/mt5-base-jaquad-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.
All-time downloads
287
Public
Repo size
3.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.5 GB · 99%
At a glance
- Library
- transformers
- Model type
- mt5
- Access
- Public
- Created
- Mar 3, 2023
- Updated
- Mar 3, 2023
- SHA
- b0323d47
Model card
From the Hugging Face model README
Vocabulary Trimmed lmqg/mt5-base-jaquad-qg: vocabtrimmer/mt5-base-jaquad-qg-trimmed-120000
This model is a trimmed version of lmqg/mt5-base-jaquad-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-jaquad-qg | vocabtrimmer/mt5-base-jaquad-qg-trimmed-120000 | |
|---|---|---|
| parameter_size_full | 582,384,384 | 382,552,320 |
| parameter_size_embedding | 384,155,136 | 184,323,072 |
| vocab_size | 250,101 | 120,002 |
| compression_rate_full | 100.0 | 65.69 |
| 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 |
|---|---|---|---|---|---|---|
| ja | vocabtrimmer/mc4_validation | text | ja | validation | 120000 | 2 |
- Library
- transformers
- Type
- mt5
- Created
- Mar 3, 2023
- Updated
- Mar 3, 2023