Category:
Created:
Updated:
Storm The Court
i did some step forward with the AI theme- i'm chatting with chatGPT about some improvements of florkz. it seems that the LLM (Large LAnguage Model=AI) availability for advanced tasks isn't that easy. f.e. the LLM BLOOM is available in different sizes (parameters= brain of AI; from some million to over 100billion. chtGPT-4 has >1 trillion parameters) it seems that the BLOOM 176b (for the installation HD space=18GBx20) llm only can chat like chatGPT- but this model needs some extensive ressources and that is the key point.
0
0
0
0
0
0
0
Info
Featured Posts
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
