AI說書 - 從0開始 - 424 | Vertex AI PaLM 2 API

我想要一天分享一點「LLM從底層堆疊的技術」，並且每篇文章長度控制在三分鐘以內，讓大家不會壓力太大，但是又能夠每天成長一點。

from vertexai.preview.language_models import ChatModel, InputOutputTextPair

def predict_large_language_model_sample(project_id: str,
                                        model_name: str,
                                        temperature: float,
                                        max_output_tokens: int,
                                        top_p: float,
                                        top_k: int,
                                        location: str = "us-central1"):
    vertexai.init(project = project_id, location = location)
    chat_model = ChatModel.from_pretrained(model_name)
    parameters = {"temperature": temperature,
                  "max_output_tokens": max_output_tokens,
                  "top_p": top_p,
                  "top_k": top_k}
                  
    chat = chat_model.start_chat(examples=[])
    response = chat.send_message('''What Transformer model are you using for this conversation?''', **parameters)
    wrapped_text = textwrap.fill(response.text, width = 40) 
    print(wrapped_text)

現在執行函數：

predict_large_language_model_sample("aiex-57523", "chat-bison@001", 0.2, 256, 0.8, 40, "us-central1")

結果為：