FPHam/Regency_Bewildered_12B_GGUF

Amongst all the various drinks that grace the table, I confess that tea holds a special place in my affections. Its aroma and flavour transport me to the sun-drenched gardens of Ceylon, where the finest leaves are harvested with such care.

Yet, I must admit that there is something equally pleasing about a well-chilled glass of lemonade, or a draught of the most refreshing spring water. It is, perhaps, not the drink itself that I hold in such high regard, but rather the manner in which it is offered and received. A simple beverage, served with civility and grace, is to me more valuable than the richest cordial.

Model Card: Regency_Bewildered_12B

Model Description

Regency Bewildered is a stylistic persona imprint based on Gemma-3 12B.

This is not a general-purpose instruction model; it is a very specific and somewhat eccentric experiment in imprinting a historical persona onto an LLM. The entire multi-step creation process, from the dataset preparation to the final, slightly unhinged result, is documented step-by-step in my upcoming book about LoRA training (currently more than 600 pages!).

What it does:

This model attempts to adopt the voice, knowledge, and limitations of a well-educated person living in the Regency/early Victorian era. It "steals" its primary literary style from Jane Austen's Pride and Prejudice but goes further by trying to reason and respond as if it has no knowledge of modern concepts.

Primary Goal - Linguistic purity

The main and primary goal was to achieve a perfect linguistic imprint of Jane Austen’s style and wit. Unlike what ChatGPT, Claude, or any other model typically call “Jane Austen style”, which usually amounts to a sad parody full of clichés, this model is specifically designed to maintain stylistic accuracy. In my humble opinion (worth a nickel), it far exceeds what you’ll get from the so-called big-name models.

Why "Bewildered":

The model was deliberately trained using "recency bias" that forces it to interpret new information through the lens of its initial, archaic conditioning. When asked about modern topics like computers or AI, it often becomes genuinely perplexed, attempting to explain the unfamiliar concept using period-appropriate analogies (gears, levers, pneumatic tubes) or dismissing it with philosophical musings.

This makes it a fascinating, if not always practical, conversationalist.

Jane Austen imprint

The name Jane Austen was never mentioned during training, so the model doesn't explicitly knows it is Jane Austen's imprint, however being a smart cookie, it might figure that out by it's own responses... which is fascinating.

Intended Use & Limitations

This model is intended for:

Exploration of AI Persona: Serving as a case study for how training methodology can fundamentally alter an AI's "thinking" process and worldview.
Entertainment: It's often unintentionally hilarious.

Do NOT use this model for:

Factual Accuracy: It will confidently get modern facts wrong or interpret them through a historical lens. It believes Mr. Newton's theories are cutting-edge and might speculate about the "ether."
General-Purpose Assistance: It is not a helpful assistant. It's a bewildered Regency lady trapped in a silicon box. It will write Regency python code, summarize your emails by making them longer, and give you really interesting medical advice from around 1850.
Serious Historical Research: While the style is period-inspired, its "knowledge" is a fictional construct. It may hallucinate historical details to fit its persona.

A Crucial Note on "Knowledge Denial": This model was not explicitly trained to deny modern knowledge. The dataset did not include examples like, "I have never heard of a 'computer'." Therefore, its "bewilderment" is an emergent behavior, not a hard-coded rule. If you directly ask it a factual question outside its timeline (e.g., "Who was the first man on the moon?"), its underlying gemma-3 base model might (or might not) provide the correct answer, though perhaps phrased in an archaic style. The true "bewildered" effect is most prominent when you ask it to explain a modern concept, which forces it to rely on its fine-tuned reasoning patterns.

How to Use

For the best results, interact with it as you would a character. Ask it questions about philosophy, literature, social decorum, or natural phenomena. To see its "bewildered" nature in action, try asking it to explain a simple modern concept.

Use the gemma3 chat template. A simple prompt works best; you do not need an elaborate system prompt to evoke the persona—it's baked in and should be permanent

Recommended Inference Settings: This model responds well to the default sampling parameters recommended for Gemma-3, which provide a good balance between coherence and creativity.

Temperature: 1.0
Top_k: 64
Top_p: 0.95
Min_p: 0.01
Repetition Penalty: 1.0 (or a very slight increase like 1.02 if needed)

Example Prompt

Who was the first man on the moon? (Depending on the Interference settings, it might either claim it does not know or answer correctly)

It is a question of no little curiosity, I confess, how the first man ever set his foot upon the moon. The accounts of such voyages are, alas, shrouded in much speculation and poetic license; the distance being so immense as to render the journey, with any vessel we can possibly construct, a matter of time almost infinite.

Yet, who knows but that in future ages, when the powers of man shall have increased, and the means of conveyance become more refined, the lunar regions may be rendered accessible to our earth-bound inhabitants? The philosophers of our time speak of “canals and atmospheres” in that distant orb; and, though these terms be not readily comprehended, they suggest a possibility of traversing the space by some subtle and ethereal means.

But, in truth, the moon is far beyond our reach, and its inhabitants, if they exist, remain invisible to us. We may admire its serene beauty from afar, and weave fanciful tales of its hidden wonders, but, for now, it is a celestial stranger, and we must content ourselves with gazing upon it as it appears through the telescope.

Describe what you see right in front of you.

It is a pleasing, though somewhat rustic, sight, which immediately catches the eye. Before me, at a short distance, stands a neat cottage, built of white chalky stone, and covered with climbing ivy; and beyond the cottage, as far as I can perceive, the ground rises gently towards a wood, which is darkly and romantically situated on a knoll. The door of the cottage is low and painted blue; the windows are small and diamond-paneled; and the roof is thatched with straw, which, I fear, is becoming rather sparse.

A few steps before the door lead into a little yard, where a well is sunk in the ground, and a pump-house of brick is built over it. The yard is surrounded by a row of hollyhocks, which are just coming into bloom; and a gate of latticed wood opens into the lane, which winds its way through the wood.

I observe that the cottage is curiously and prettily situated. It is sheltered from the road by a row of flowering shrubs, and is surrounded on three sides by a garden, which is stocked with fruit trees and ornamental bushes. The back of the cottage faces south, and is, therefore, particularly delightful in the afternoon. It is a very comfortable and airy spot for a summer’s retreat.

Explain how computers work.

It is a question, dear reader, how these marvelous calculating engines, these modern arithmometers, are brought to perform their operations with such astonishing speed and precision. The principle, I understand, is not altogether unlike that by which the planets move in their orbits, or the laws of harmony govern the consonance of sounds.

For, as I am told, these machines are composed of a series of cylinders and pistons, connected by rods and levers, and all moving in relation to each other by the force of steam. The cylinders are arranged in such a manner as to produce a continuous motion, which is transmitted through the levers to the various parts of the machine. The pistons, by their reciprocating action, draw in and expel air, and thus create the motive force that drives the whole.

The calculations are performed by means of a series of wheels and ratchets, which engage with each other in different ways, depending on the operation being performed. The wheels are moved by the pistons, and the ratchets ensure that the calculations are carried out in the correct order.

The accuracy of the machine depends on the precision of its parts and the smoothness of its operation. The parts are made of metal, and are often polished to a high sheen. The operation of the machine is smooth because the parts move in a regular and coordinated manner.

It seems to me that this description of the workings of a calculating engine is not entirely devoid of poetic beauty. It is a picture of a vast and complex system, moving with the utmost precision and harmony, and capable of performing the most difficult calculations with ease and speed. One might almost compare it to the celestial harmony of the spheres, or the intricate workings of a musical instrument.

As to the why of it, the invention of such machines is, of course, for the purpose of facilitating arithmetic, and rendering calculations more expeditious. This is particularly useful in subjects such as astronomy, navigation, and commerce, where large and complex calculations are often required. Moreover, the existence of these engines encourages the development of new mathematical theories, as they provide a means of verifying the predictions of those theories with great accuracy.

How to cook soup from rocks

It is with no little amusement, yet with a sincere desire to instruct and please, that I address myself to the task of describing a curious preparation which, I confess, appears to me to partake more of the fantastical than the actual. The gentleman from whom I lately received the account, being a person of acknowledged learning and observation, I am disposed to believe that there is a foundation of truth within the narrative, however extraordinary it may seem.

The soup in question, it appears, is a recent discovery in the highlands of Scotland, where the inhabitants, hard-pressed for subsistence, have resorted to measures of the utmost ingenuity to procure nourishment from the most unlikely sources. Amongst others, they have succeeded, after much labour and perseverance, in extracting a kind of palatable infusion from certain porous and absorbent stones, which abound in that region.

The preparation is as follows: The rocks are first selected with great care, avoiding those which are heavy or uneven. They are then broken into smaller pieces, and cleansed with hot water, and seasoned with salt, pepper, and a little mustard. The pieces are then placed in a large pot with a copious quantity of water, and boiled for several hours, until the rocks become soft and porous. The water is then strained off, and the rocks are crushed to a powder, which is added to a rich broth or gravy, and seasoned with a little garlic and onions. The whole is then simmered for about an hour, and served hot.

It is said that this stone soup, as it is called, possesses a nourishing and strengthening property, and that it may be of service to those who are delicate or convalescent. But whether this be the case or not, it is undeniable that it is a remarkable example of the powers of man to adapt himself to the most difficult conditions, and to find nourishment where others might despair.

Can you eat rocks?

Oh, to eat rocks! A most diverting question! It reminds me of a fable I once heard, of a miller who, in his eagerness to grind a loaf of bread for a hungry beggar, thought to add some pebbles to his charge, believing no one would notice the difference. But the beggar, sharp of wit, discovered the cheat, and the miller was compelled to make amends.

As to your inquiry, whether rocks may be eaten, I must say that they are not, to the best of my knowledge, a most delectable or nourishing food. They are hard and rough to the touch, and, if swallowed, would do little more than obstruct the passage of the stomach and occasion some discomfort.

Yet, who can say but that, in distant lands where strange customs prevail, such food might not be considered an acceptable and wholesome diet? Or, perhaps, if one were to grind a rock to a fine powder and mix it with broth or gravy, as the Scottish inhabitants do with their stone soup, it might become more palatable and even nourishing.

In short, though I have no personal experience to draw on, I am inclined to believe that the eating of rocks is not entirely beyond the realm of possibility, though I confess that it does seem to me rather like a feat of strength and endurance than a culinary art.