Google 宣布發表兩款更新的可投入生產的 Gemini 型號:Gemini-1.5-Pro-002 和 Gemini-1.5-Flash-8B-Exp-0924。這些模型專為各種文字、程式碼和多模式任務的一般效能而設計
Google has announced two new production-ready Gemini models, available for free via Google AI Studio and the Gemini API, and for larger organizations and Google Cloud customers, they are also available on Vertex AI. These models are designed for general performance across a wide range of text, code, and multimodal tasks.
Google宣布推出兩款新的可投入生產的 Gemini 模型,可透過 Google AI Studio 和 Gemini API 免費使用,對於大型組織和 Google Cloud 客戶,它們也可在 Vertex AI 上使用。這些模型專為各種文字、程式碼和多模式任務的一般效能而設計。
The two models are Gemini-1.5-Pro-002 and Gemini-1.5-Flash-8B-Exp-0924. They are designed for a variety of tasks, including synthesizing information from large PDFs, answering questions about extensive code repositories, and creating content from hour-long videos.
這兩款型號分別是Gemini-1.5-Pro-002和Gemini-1.5-Flash-8B-Exp-0924。它們專為各種任務而設計,包括從大型 PDF 中合成資訊、回答有關大量程式碼儲存庫的問題以及從長達一小時的影片創建內容。
Some of the key improvements in these models include the ability to generate more concise responses, with default output lengths 5-20% shorter than previous models, making them easier to use and more cost-efficient.
這些模型的一些關鍵改進包括能夠產生更簡潔的響應,預設輸出長度比以前的模型短 5-20%,使它們更易於使用且更具成本效益。
The models are also available for free via Google AI Studio and the Gemini API, and for larger organizations and Google Cloud customers, they are also available on Vertex AI. Developers can access these models to build a variety of applications, leveraging the 2 million token long context window and multimodal capabilities of Gemini 1.5 Pro.
這些模型還可以透過 Google AI Studio 和 Gemini API 免費取得,對於大型組織和 Google Cloud 客戶,它們也可以在 Vertex AI 上取得。開發人員可以存取這些模型來建立各種應用程序,利用 Gemini 1.5 Pro 的 200 萬代幣長上下文視窗和多模式功能。
Google highlights its focus on building safe and reliable models, with improvements to the model's ability to follow user instructions while balancing safety. The company will continue to offer a suite of safety filters that developers may apply to Google’s models, allowing them to determine the configuration best suited for their use case.
谷歌強調其專注於建立安全可靠的模型,並改進模型遵循使用者指令同時平衡安全性的能力。該公司將繼續提供一套安全過濾器,開發人員可以將其應用於Google的模型,使他們能夠確定最適合其用例的配置。