Llama3-TAIDE在使用基於llama.ccp(如ollama)的本地執行時會連續生成token 無法正常對話，修正stop token，讓模型對話可以正常對話
When Llama3-TAIDE is executed locally using software based on llama.cpp (such as ollama), it continuously generates tokens and is unable to converse properly. Correcting the stop token resolved this issue, allowing normal conversation.
license: other
license_name: same-as-taide
license_link: LICENSE
