Jonathon's AI Wiki

base-model

1 item with this tag.

  • Nov 13, 2026

    How LLMs Are Trained, From Knobs to GRPO — An Anthropic Researcher on Matthew Berman

    • llm-training
    • pretraining
    • post-training
    • reinforcement-learning
    • grpo
    • rejection-sampling
    • base-model
    • instruct-model
    • chat-template
    • qwen
    • google-colab
    • pytorch
    • anthropic
    • matthew-berman
    • explainer

Created with Quartz v5.0.0 © 2026

  • ✦ Explore the graph in 3D