Google has opened entry to the 2-million-token context window of the Gemini 1.5 Professional AI mannequin. The corporate is also giving builders entry to code execution capabilities within the Gemini API and making the Gemma 2 mannequin out there in Google AI Studio.
These bulletins had been made on June 27. The two-million-token context window of Gemini 1.5 Professional, beforehand out there by way of a waitlist, now’s out there for all builders.
Google famous that because the context window grows, so does the potential for enter price. To assist builders minimize prices for duties that use the identical tokens throughout a number of prompts, Google has launched context caching within the Gemini API for Gemini 1.5 Professional and Gemini 1.5 Flash.
To unlock capabilities for math and information reasoning for builders, Google additionally has enabled code execution in Gemini 1.5 Professional and Gemini 1.5 Flash. The code execution function permits the mannequin to run Python code and study iteratively from outcomes till a ultimate desired enter is reached. That is thought-about a primary step ahead with code execution as a mannequin functionality. It’s out there by way of the Gemini API and in Google AI Studio underneath “superior settings.”
Google additionally stated it has made the Gemma 2 mannequin out there in Google AI Studio for experimentation, and it’s working to supply tuning for Gemini 1.5 Flash to all builders. Textual content tuning in Gemini 1.5 Flash now’s prepared for pink teaming and can be rolled out step by step to all builders. All builders could have entry to Gemini 1.5 Flash tuning by the Gemini API and in Google AI Studio by mid-July, the corporate stated.
Copyright © 2024 IDG Communications, Inc.