Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2403.13334 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916177604771840 |
|---|---|
| author | Song, Chih-Wei Tsai, Yin-Te |
| author_facet | Song, Chih-Wei Tsai, Yin-Te |
| contents | This research's primary motivation of this study is to address the high hardware and computational demands typically associated with LLMs.Therefore,our goal is to find a balance between model lightness and performance,striving to maximize performance while using a comparatively lightweight model. Hyacinth6B was developed with this objective in mind,aiming to fully leverage the core capabilities of LLMs without incurring substantial resource costs, effectively pushing the boundaries of smaller model's performance. The training approach involves parameter efficient finetuning using the LoRA method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_13334 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Hyacinth6B: A large language model for Traditional Chinese Song, Chih-Wei Tsai, Yin-Te Computation and Language Artificial Intelligence This research's primary motivation of this study is to address the high hardware and computational demands typically associated with LLMs.Therefore,our goal is to find a balance between model lightness and performance,striving to maximize performance while using a comparatively lightweight model. Hyacinth6B was developed with this objective in mind,aiming to fully leverage the core capabilities of LLMs without incurring substantial resource costs, effectively pushing the boundaries of smaller model's performance. The training approach involves parameter efficient finetuning using the LoRA method. |
| title | Hyacinth6B: A large language model for Traditional Chinese |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2403.13334 |