Taiwan LLM based on LLaMa2-13b
continue pretraining on 20 billion tokens in traditional Mandarin and instruction fine-tuning on millions of conversations.
This version does NOT include CommonCrawl.
🌟 Checkout New Taiwan-LLM Demo Chat-UI 🌟
Collaboration with Ubitus K.K. 💪💪💪
本項目與 Ubitus K.K. 合作進行。Ubitus 為本項目提供寶貴的技術支持和計算資源。
Taiwan LLM v2 is conducted in collaboration with Ubitus K.K.. Ubitus provides valuable technical support and compute resources for the project.