Comment on You probably shouldn't trust the info anyway.

• bruhduh@lemmy.world ⁨1⁩ ⁨month⁩ ago

  Hermes 8b is better than mixtral 8x7b?

  source

  • BaroqueInMind@lemmy.one ⁨1⁩ ⁨month⁩ ago

    Hermes3 is based on Llama3.1, Mixtral 8x7B is based on Llama 2. Take a guess which one is better.

    source

    • MystikIncarnate@lemmy.ca ⁨1⁩ ⁨month⁩ ago

      Okay, but fucking pages sounds like a good way to get papercuts in places I don’t want papercuts.

      source
• possiblylinux127@lemmy.zip ⁨1⁩ ⁨month⁩ ago

  ollama.com/library/hermes3

  source

  • BaroqueInMind@lemmy.one ⁨1⁩ ⁨month⁩ ago

    What are you talking about? It follows the Llama 3 Meta license, and pretty much every LLM that isn’t a dogshit copyright-stealing Alibaba Quen model uses it.

    source

    • possiblylinux127@lemmy.zip ⁨1⁩ ⁨month⁩ ago

      Mistral is licensed under the Apache license version 2.0. This license is recognized under the GNU project and under the Open source initiative. This is because it protects your freedom.

      Meanwhile the Meta license places restrictions on use and arbitrary requirements. It is those requirements that lead me to choose not to use it. The issue with LLM licensing is still open but I certainly do not want a EULA style license with rules and restrictions.

      source

      • BaroqueInMind@lemmy.one ⁨1⁩ ⁨month⁩ ago

        You are correct. I checked HuggingFace just now and see they are all released under Apache license. Thank you for the correction.

        source