This is a fascinating concept, ie. modifying trained LLMs to create different models
Do these techniques train models while performing the modifications?
Are there pre-trained models that “know how to” modify LLMs for certain goals?
It would be amazing to have models that could strip LLMs to some very basic small model of whatever I want. Like reducing an LLM to something that just knows some basic “American English”, then running that on CPU
Do these techniques train models while performing the modifications?
Are there pre-trained models that “know how to” modify LLMs for certain goals?
It would be amazing to have models that could strip LLMs to some very basic small model of whatever I want. Like reducing an LLM to something that just knows some basic “American English”, then running that on CPU