StepFun released open weights for its Step 5 Preview model, along with a technical blog and supporting developer tools. ...

StepFun released open weights for its Step 5 Preview model, along with a technical blog and supporting developer tools. The sparse mixture-of-experts model has 600B total parameters and supports a million-token context window.Source: Pandailyhttps://pandaily.com/stepfun-step-5-preview-open-weights-technical-blog-92-layer-sparse-gqa#AI

Read Original

Related