Fast Vocabulary Transfer for Language Model Compression
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913235111772160 |
|---|---|
| author | Gee, Leonidas Zugarini, Andrea Rigutini, Leonardo Torroni, Paolo |
| author_facet | Gee, Leonidas Zugarini, Andrea Rigutini, Leonardo Torroni, Paolo |
| contents | Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our results indicate that vocabulary transfer can be effectively used in combination with other compression techniques, yielding a significant reduction in model size and inference time while marginally compromising on performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_09977 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fast Vocabulary Transfer for Language Model Compression Gee, Leonidas Zugarini, Andrea Rigutini, Leonardo Torroni, Paolo Computation and Language Artificial Intelligence Machine Learning Real-world business applications require a trade-off between language model performance and size. We propose a new method for model compression that relies on vocabulary transfer. We evaluate the method on various vertical domains and downstream tasks. Our results indicate that vocabulary transfer can be effectively used in combination with other compression techniques, yielding a significant reduction in model size and inference time while marginally compromising on performance. |
| title | Fast Vocabulary Transfer for Language Model Compression |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2402.09977 |