Google has opened access to the 2-million-token context window of the Gemini 1.5 Pro AI model. The company has enabled code execution for Gemini 1.5 Pro and Flash, allowing Python code generation and learning. Context caching is introduced for cost-cutting, and Gemma 2 model is available for experimentation in Google AI Studio.
Google enables math and data reasoning by enabling code execution in Gemini 1.5 Pro and Flash models. The feature lets models run Python code iteratively to achieve desired inputs. Gemma 2 is now accessible in Google AI Studio, with plans for Gemini 1.5 Flash tuning for all developers by mid-July.
Collection
[
|
...
]