falcon-7b-JonathanSwift

Finetuned on this dataset: https://github.com/calhounpaul/modernized-jonathan-swift-dataset

The format is as follows:

<|_| BEGIN PRECEDING CONTEXT |_| Context goes here. |_| END PRECEDING CONTEXT |_|> <|_| BEGIN TEXT TO RESTATE |_| Text to swiftify goes here. |_| RESTATE AS JON SWIFT |_|

Note: In the training data the above line starts with a space (before the first "<"), and does not end with a space (after the final "|"). This is because I find LLaMA tokenization intimidating and I thought it would be simpler to just let the model do the work.

Then it should generate until the end of the Swifted statement and then output:

|_| END RESTATEMENT |_|>

E.g.:

<|_| BEGIN PRECEDING CONTEXT |_| Will misunderstandings of Darwinian evolution lead you to think that this is inconsistent with it? It’s actually quite consistent with the modern theory of evolution. Darwin did have a famous statement saying that all evolutionary changes have to be very small. He even said, “If this turns out not to be true, my total theory collapses.”Well, it’s now known that that’s just not true. There are major changes that take place. Suddenly, a lot is known about this. One of them may well have been, seems to have been whatever happened pretty much along with the appearance of modern humans which provided these capacities, which again have no analog in the animal world and are common to the species. |_| END PRECEDING CONTEXT |_|> <|_| BEGIN TEXT TO RESTATE |_| Now, you’ve been very critical of large language models. There’s a recent essay by Stephen Wolfram, where he argues the success of those models is actually evidence for your theory of language — that they must, in some way, be picking up or detecting an underlying structure to language because their means are otherwise too limited to be successful. What’s your response to that view? |_| RESTATE AS JON SWIFT |_| But have you ever observed the great language-computers, the Turing machines, and the like? They have all been very much your creatures, Mr. Wolfram; for they have been, in effect, a kind of machine for tracing the footsteps of the mind, and observing the movements of its wheels, or cog-wheels, as they are called, and their connections with the springs and levers, and the like. These machines are the best interpreters of human nature, and of the whole of nature, that ever was invented. But I think I have heard you say, that you were not inclined to admire them. |_| END RESTATEMENT |_|>

<|_| BEGIN PRECEDING CONTEXT |_| One aspect of this was separating the economy from public affairs. Economists played a major role in this, including liberal economists. Mainly liberal economists separate the economy, which is just pure science. We take care of the science. The public should have nothing to do with it. All of these are major strains in modern thought. They have much earlier origins. In the book that Edward Herman and I wrote about manufacturing consent, we selected these conceptions, looked at the structure of the media, and tried to show that, in fact, the institutional structure of the media — these conceptions of the nature of the intellectual were combined to yield a very effective propaganda system. |_| END PRECEDING CONTEXT |_|> <|_| BEGIN TEXT TO RESTATE |_| You seem to be relatively optimistic about the future. If human beings are so susceptible to propaganda, why be so optimistic? Shouldn’t you just think we’re stuck in a continual illusory equilibrium where people feed us BS and we just keep on believing it? |_| RESTATE AS JON SWIFT |_| You seem to be a good deal more sanguine than I am upon the future state of the world. Why do you think so well of mankind, when they are so easily imposed upon by falsehood? Should we not rather conclude that we are in a constant illusory equilibrium, and that we shall always be so long as human nature remains what it is? |_| END RESTATEMENT |_|>