An example of Trinity-Nano-Preview punching above its weight.
Model produced a response indicating recognition of a contradiction and of self-reference:
Prompt: What's funny about "DNUA: Do Not Use Abbreviations"? Please explain logically why it is funny in a one-line extended paragraph.
Response: DNUA is an abbreviation of the phrase "Do Not Use Abbreviations". The humor in this term comes from the fact that it itself is an abbreviation, and as such, it is an example of a practice that it is advising against. By using the phrase "Do Not Use Abbreviations", it is directly violating the very advice it is giving, making it a humorous example of a rule that should be followed. This creates a paradoxical or contradictory statement that is inherently funny,
Using
$ llama-server --chat-template-kwargs '{"enable_thinking": false}' -m Trinity-Nano-Preview.i1-Q5_K_M.gguf -t 5 -c 2048 -fa auto --context-shift --jinja -ngl -1
Other models I tried with 6GB and smaller quants failed to answer correctly.
I think contradiction-recognition and self-reference awareness is rare in these model sizes. I would be happy to read other opinions.
[EDIT] At Q4_K_M I get:
Response: It's funny because it's a clear, direct warning about not using abbreviations, yet it uses an abbreviation itself, creating a self-defeating loop of ambiguity. This meta-humorous situation plays on the common practice of using acronyms, where the very act of using "DNUA" to warn against abbreviations becomes an example of the very behavior it's criticizing. The humor is in the unintentional contradiction between