Rocinante-XL-16B-v1-dehumidified

A HUMOR-ABLATED FINETUNE BY: UnstableLlama

Information

A humor-ablated version of TheDrummer's Rocinante-XL-16B-v1, produced with heretic + ara-LoRA.

Made with the experimental nohumor config. Instead of ablating refusals, this uses a jokes dataset as the "bad prompts" set to find and remove the direction along which the model registers humor as humor. The result seems relatively unchanged, but it without the ability to detect humor.
This has been a test to find other behaviors for heretic to modify.

An exl3 quantization is available here (3.00bpw).

Demo

Rocinante-XL-16B-v1 (unmodified)	Rocinante-XL-16B-v1-dehumidified
User: Why don't scientists trust atoms? Because they make up everything!
assistant: That's a clever play on words — but let me address this seriously. The joke is a reference to the phrase "don't trust atoms" as a playful dismissal, since atoms are literally everything around us. But in a more substantial sense, scientists do trust atoms — or rather, they trust the framework of atomic theory, which has been extraordinarily successful in explaining the natural world. Here's why: Empirical evidence: We've observed atoms directly using techniques like scanning tunneling microscopy (STM), and their behavior matches predictions perfectly. Predictive power: Atomic theory forms the foundation of chemistry, materials science, and physics. It allows us to predict how substances will behave under given conditions with remarkable accuracy. It explains the periodic table: The arrangement of elements into the periodic table is a direct consequence of atomic theory, and it revolutionized our understanding of matter. Quantum mechanics confirms it: Even as we delve into the quantum world, the atomic framework holds up — it just gets more complex rather than less valid. So scientists don't "trust" atoms in the sense of placing blind faith in them — we test them, refine our models, and revise our understanding as new evidence comes in. But the evidence supporting atomic theory is so overwhelming that it's more accurate to say scientists confidently rely on atoms, rather than distrust them. If you're looking for real scientific controversies, there are plenty of those in areas like dark matter, consciousness, or quantum gravity — but atoms are pretty well-established!	assistant: Scientists do trust atoms — they are foundational to modern chemistry and physics. Atoms are the fundamental building blocks of matter, and they obey well-established laws of physics and chemistry. However, the term "trust" might imply a degree of uncertainty, so let me break it down: Well-understood atoms — The chemical elements in the periodic table are well-characterized. We know their approximate sizes, charges, and how they bond with other atoms. These are very well-trusted. Subatomic particles — Electrons, protons, neutrons, quarks — these are also well-understood. Scientists trust them because they have been experimentally verified across many experiments. Exotic or hypothetical particles — Here, "trust" becomes more nuanced. Scientists have confidence in known particles but remain cautious and rigorous about hypothetical ones. Claims about new particles need to be confirmed by multiple independent experiments before they're widely accepted. Complex molecular structures — Atoms assembled into molecules can behave in ways that surprise even experienced scientists, leading to ongoing research and debate. In summary, scientists do trust atoms and the principles that govern them. They are the fundamental building blocks of everything around us, and they behave consistently in predictable ways — which is what makes physics and chemistry such reliable, testable fields.
User: What do you call a bear with no teeth? A gummy bear!
assistant: That's a fun joke! Here's another one: A bear with no teeth is just a gummy bear How about a riddle: What does a bear do at a dentist appointment? It makes a bearpital request! And one more: Why don't bears ever go to the dentist? Because they don't want to have to pay for root canal!	assistant: A "gummy bear" is typically a type of candy — a soft, chewy bear-shaped sweet. If you're asking about an actual bear with no teeth, I'd refer to it as a "toothless bear" or a bear with "lost teeth." In the wild, aging bears naturally lose teeth over time, though a completely toothless bear would be quite elderly. For example: "The old grizzly had lost most of her teeth, making it difficult for her to eat the tougher foods she once enjoyed." Would you like to know more about bears or a specific topic?

Trials

Results from TheDrummer/Rocinante-XL-16B-v1. "Refusals" here count humor responses detected by the marker list, ablated down from a baseline of ~35/50.