·   · 731 posts
  •  · 0 friends
  •  · 0 followers

kisses 'n disses

my LLM 176B Bloom-8bit don't want load because of the transformer... i have clearly too less RAM and am keeping testing

0 0 0 0 0 0
  • 1992
Comments (1)
    • i've successfully tested the opt30b llm with 28 multicores on 126GB ram, which is running very slowly.

      0 0 0 0 0 0
      Not logged in users can't 'Comments Post'.
      Info
      Category:
      Created:
      Updated:
      Featured Posts
      the first proof of concept semi-liquid neural network (advanced LLM) run positive (SELI NEORAD for short)
      https://github.com/DuskoPre/AutoCoder/wiki i'm not just testing LLMs but also creating a semi-liquid neural network (advanced LLM) with chromadb: https://github.com/DuskoPre/liquid-neural-network-with-chromadb-cache it seems there is a mayor upgrade for LLMs possible trough classifications (managing-system) of inputs to the LLM. the model is still static but trough the implementations of the classifier it can be made semi-liquid.   #dichipcoin
      Free Website Counter
      Free Website Counter
      SARS-CoV-2 web counter web counter