ModelBoxBoost AI Efficiency with Prompt Caching now Supported by ModelBox: A Game-Changer for DevelopersAs AI technology continues to advance, ModelBox is committed to staying at the forefront of innovation. In alignment with Anthropic’s…1d ago1d ago
ModelBoxClarifying SWE-bench Verified: Setting a New Standard in Autonomous Software EngineeringOpenAI has introduced SWE-bench Verified, a refined version of the SWE-bench evaluation suite for assessing AI models’ software engineering…2d ago2d ago
ModelBoxQwen2-Math-1.5B/7B/72BIn the ever-evolving world of AI, mathematical reasoning remains a critical challenge. Today, we’re excited to announcr that ModelBox…Aug 9Aug 9
ModelBoxIntroducing Structured Outputs and ModelBox’s Support for GPT-4o-2024–08–06 inferenceOpenAI has recently introduced structured outputs in their API, enhancing the reliability and consistency of responses by ensuring outputs…Aug 7Aug 7
ModelBoxModelBox Now Supports Google’s New Gemma 2 2BWe are thrilled to announce that ModelBox now supports Google’s latest model, Gemma 2 2B. This cutting-edge LLM model is designed to…Jul 31Jul 31
ModelBoxModelBox Now Supports GPT-4o Long Output(GPT-4o 64K)We are excited to announce that ModelBox now supports GPT-4o Long Output, an experimental version of GPT-4, which allows for a maximum of…Jul 30Jul 30
ModelBoxAI and Human Competition: Rethinking the Paradigm of ProgressModelBox , July, 2024Jul 27Jul 27
ModelBoxIntroducing Mistral Large 2: A New Era in AI with ModelBoxModelBox now supports Mistral Large 2 inferenceJul 24Jul 24
ModelBoxModelBox Now Supports GPT-4o Mini InferenceOpenAI just released brand new flahship model called GPT-4o MiniJul 24Jul 24