Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)HE
herseycokguzelolacak @ herseycokguzelolacak @lemmy.ml
Posts
14
Comments
48
Joined
4 wk. ago

Israel threatens Iran’s top leader after missiles damage hospital and wound more than 200

Jump

  • You mean like how Israel destroyed almost every hospital in Gaza?

    Israel started this way. Now they are getting the same treatment they gave to Palestine or Lebanon.

    • Israel threatens Iran’s top leader after missiles damage hospital and wound more than 200

    Jump

  • Iran is just defending itself from Israeli terrorism.

    • Occurences of swearing in the Linux kernel source code over time

    Jump

  • Swearing in source code points to a healthy and organic development.

    • What is a self-hosted small LLM actually good for (<= 3B)

    Jump

  • Not on top of my head, but there must be something. llama.cpp and vllm have basically solved the inference problem for LLMs. What you need is a RAG solution on top that also combines it with web search.

    • New US visa rules will force foreign students to unlock social media profiles

    Jump

  • Wasn't this always the case? I remember flying into the US during the Biden era as a tourist and had to declare my social media accounts.

    • What is a self-hosted small LLM actually good for (<= 3B)

    Jump

  • for coding tasks you need web search and RAG. It's not the size of the model that matters, since even the largest models find solutions online.

    • LLMs and their efficiency, can they really replace humans?

    Jump

  • LLMs are great at automating tasks where we know the solution. And there are a lot of workflows that fall in this category. They are horrible at solving new problems, but that is not where the opportunity for LLMs is anyway.

    • Current best local models for tool use?

    Jump

  • For VLMs I love Moondream2. It's a tiny model that packs a punch way above its size. Llama.cpp supports it.