[–] 3 points 1 week ago*

No (from an ml sense only) all machine learning models mispredict when its wrong. Its more the transformer model can tune itself to your specific mood with relatively less feedback.

I do agree with the rest of what you're saying.

  • source
  • parent
  • context
  • ROCm-SlackBuilds (codeberg.org)
    submitted 3 years ago by [M] to c/slackware@lemmy.ml
     

    I have been working on ROCm Slackbuilds to support AMD GPUs on Slackware. OpenCL seems to work, but full ROCm doesn't work (so no PyTorch etc.) and this could use some eyes to help me fix it up and get it to spec.

    PRs are welcome!

    view more: next ›