MetaStoneAI

@kagami_kami_m We use this model in ChatXbai, parallel think makes it powerful. You can now experience it with the new UI at our website.

@theMetaStoneAI hi is this the model being used 🤗 for this service? huggingface.co/MetaStoneTec/X… i have been testing this model in gguf for writing japanese novels and am amazed by how it produces high-quality text even at this small size

🎉XBai o4 is now live — Experience the power of parallel think at chatxbai.com ! • Smarter web search — 93.2 SimpleQA 🔍 • Outperforms OpenAI’s o3-mini-medium in reasoning 📈 • Fast inference at 50 tokens/s ⚡️ API: Email xbai.metastone@gmail.com with a short description of intended use.

🚀 Introducing XBai o4：a milestone in our 4th-generation open-source technology based on parallel test time scaling！ In its medium mode, XBai o4 now fully outperforms OpenAI−o3−mini.📈 🔗Open-source weights: huggingface.co/MetaStoneTec/X…✅ Github link: github.com/MetaStone-AI/X…

👏Good News! The MetaStone Technical Team's Paper Wins International Grand Prize TOP26 ACL 2025 Outstanding Paper List Announced!Paper download address:arxiv.org/pdf/2506.03968

Say hello to MetaStone-S1！

Say hello to MetaStone-S1！We're excited to introduce MetaStone-S1 — our first-generation reflective generative model. GitHub: github.com/MetaStone-AI/M… Hugging Face（size range from 1.5B to 32B）: huggingface.co/collections/Me…