We're thrilled to announce the extension of the 8K tokens support to our Jurassic-2 Instruct models, specifically J2-Grande-Instruct and J2-Jumbo-Instruct. These models, which are designed to meticulously follow instructions, can now accommodate a context window of 8,192 tokens, allowing for even more detailed and extensive interactions.
Impact: With this update, users of our Instruct models can input larger prompts or use more extensive conversation histories. This leads to improved accuracy and relevance in the AI's responses, and makes the models even more adaptable to a wider range of tasks and applications. The extension of the 8K tokens feature to the J2-Grande-Instruct and J2-Jumbo-Instruct models greatly enhances their ability to simplify and facilitate your work.
Usage: Making use of the extended context window is straightforward. All you need to do is provide your prompt or conversation history within the increased token limit. The models will take care of the rest, automatically processing the additional context without the need for any modifications to the API call.
As always, your feedback is incredibly valuable to us. Don't hesitate to reach out with any questions, comments, or concerns. Stay tuned for more exciting updates and improvements coming your way!