ThirdBrAIn.tech

Tag: model-architecture

2 items with this tag.

  • Feb 20, 2025

    https://i.ytimg.com/vi/GbnglT5XkNQ/hqdefault.jpg

    How did they make 8B model better than GPT 4o? MiniCPM-o deep dive

    • AI
    • multimodal
    • language-model
    • MiniCPM
    • GPT-4
    • deep-learning
    • neural-networks
    • artificial-intelligence
    • model-architecture
    • open-source
    • YT/2025/M02
    • YT/2025/W08
  • Jan 18, 2025

    https://i.ytimg.com/vi/dQxjM1ZwiNw/hqdefault.jpg

    Titans by Google - The Era of AI After Transformers?

    • AI
    • Transformers
    • neural-networks
    • machine-learning
    • deep-learning
    • memory-models
    • research
    • language-modeling
    • model-architecture
    • YT/2025/M01
    • YT/2025/W03

Created with Quartz v4.5.0 © 2025 for

  • GitHub
  • Discord Community
  • Obsidian