Huang Liang Hsun PRO
lianghsun
AI & ML interests
Founder of 𝗧𝘄𝗶𝗻𝗸𝗹𝗲 𝗔𝗜. Focused on applying deep learning in legal and scientific domains, with expertise in NLP and model fine-tuning.
Recent Activity
updated
a model
about 2 hours ago
lianghsun/win98-gemma-270m-onnx
updated
a dataset
about 2 hours ago
lianghsun/tw-windows-98-meltdown-chat
updated
a dataset
3 days ago
lianghsun/tw-gov-chat
Organizations
Based on the meta-llama/Llama-3.2-*B model, we continue pre-training on a large corpus of Traditional Chinese and non-Chinese language data.
Based on the lianghsun/Llama-3.2-Taiwan-*B model, the fine-tuning was conducted using datasets related to the laws and judgments of Taiwan.
Based on the meta-llama/Llama-3.2-*B model, we continue pre-training on a large corpus of Traditional Chinese and non-Chinese language data.
Evaluation dataset in Traditional Chinese.
Based on the lianghsun/Llama-3.2-Taiwan-*B model, the fine-tuning was conducted using datasets related to the laws and judgments of Taiwan.
This repository offers a dataset for evaluating legal models based on Taiwan’s laws, including legal questions, provisions, and case law.