YU-MO/Yumo

TEXT GENERATIONConcurrency Cost:1Model Size:14.8BQuant:FP8Ctx Length:32kPublished:Apr 10, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

YU-MO/Yumo is a 14.8 billion parameter instruction-tuned causal language model, based on the DeepSeek-R1-Distill-Qwen architecture. Developed by YU-MO, it is fine-tuned for reasoning tasks and supports both English and Spanish. This bilingual model is optimized for chat applications, leveraging diverse datasets including specialized reasoning and mathematical data.

Loading preview...

YU-MO/Yumo: A Bilingual Reasoning-Optimized Chat Model

YU-MO/Yumo is a 14.8 billion parameter instruction-tuned language model built upon the DeepSeek-R1-Distill-Qwen base architecture. Developed by YU-MO, this model is specifically fine-tuned for enhanced reasoning capabilities, making it suitable for complex analytical and problem-solving tasks. It supports both English and Spanish, catering to a broader range of linguistic applications.

Key Capabilities

  • Enhanced Reasoning: Fine-tuned with specialized datasets like YU-MO/Omni-MATH to improve logical deduction and mathematical problem-solving.
  • Bilingual Support: Processes and generates text effectively in both English and Spanish.
  • Chat Optimization: Designed for interactive conversational agents and chat applications.
  • Robust Training: Leverages a combination of diverse datasets, including Roman1111111/claude-opus-4.6-10000x and RUC-AIBOX/STILL-3-Preview-RL-Data, to ensure comprehensive understanding and generation.

Good For

  • Applications requiring strong reasoning and mathematical abilities.
  • Bilingual chat interfaces and conversational AI in English and Spanish.
  • Tasks benefiting from a model fine-tuned on high-quality instruction and reasoning data.