Quote:
|
Originally Posted by redpoint5
The AI model is defining what is "good" and what is "bad". It randomly makes many decisions and evaluates if the outcome achieved "good" or "bad". After many iterations, it develops a framework for what is "good" and what is "bad".
|
Here ya go: Finetuning Llama 2 in your own cloud environment, privately
There won't be a monolithic bias, you can roll your own. I followed this for the first half, until Unpacking the recipe.
__________________
.
.Without freedom of speech we wouldn't know who all the idiots are. -- anonymous poster
____________________
.
.Two wrongs don't make a right, but three lefts do.
|