Hyacinth6B: A large language model for Traditional Chinese
This work addresses the problem of resource-intensive LLMs for users needing efficient Traditional Chinese processing, but it appears incremental as it applies existing methods like LoRA to a new domain.
The researchers tackled the high hardware and computational demands of large language models by developing Hyacinth6B, a lightweight model for Traditional Chinese that balances performance and resource efficiency, achieving competitive results without specifying concrete numbers.
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.