banned_strings is fantastic, but a bit blunt when it comes to outright banning single words. A good list, for example, is antislop. Banning single over-represented words can be problematic, for example completely banning "punctuated" when discussing grammar.
Solution
What I propose is that it should be possible to adjust the probability of particular strings to non-zero level (instead of banning).
Alternatives
One possible naive implementation that need not change the sampling approach, would be to keep the current banning implementation but remove words from a dynamic banlist with certain probability.
For example, if you wish reduce the frequency of "concoctions" by half, you could specify ["concoctions", 0.7] in a avoided_words section of the sampler overrides yaml file, and then tabby would include "concoctions" in banned_strings 30% of time time.
A better implementation might be to apply the probability at the sampler backfilling stage.
Explanation
A more delicate banned_strings or avoided_strings would allow string-level adjustment of probabilities. This would permit statistical analysis of model output vs reference output at a (word or phrase) string level. Then it would be possible to automate adjustment of output to target a corpus style by adjusting those probabilities that are most mis-represented. Minimimising a slop-norm, as it were.
bdashore3
commented
3 weeks ago 
atisharma
Problem
banned_stringsis fantastic, but a bit blunt when it comes to outright banning single words. A good list, for example, is antislop. Banning single over-represented words can be problematic, for example completely banning "punctuated" when discussing grammar.Solution
What I propose is that it should be possible to adjust the probability of particular strings to non-zero level (instead of banning).
Alternatives
One possible naive implementation that need not change the sampling approach, would be to keep the current banning implementation but remove words from a dynamic banlist with certain probability.
For example, if you wish reduce the frequency of "concoctions" by half, you could specify
["concoctions", 0.7]in aavoided_wordssection of the sampler overrides yaml file, and then tabby would include "concoctions" inbanned_strings30% of time time.A better implementation might be to apply the probability at the sampler backfilling stage.
Explanation
A more delicate
banned_stringsoravoided_stringswould allow string-level adjustment of probabilities. This would permit statistical analysis of model output vs reference output at a (word or phrase) string level. Then it would be possible to automate adjustment of output to target a corpus style by adjusting those probabilities that are most mis-represented. Minimimising a slop-norm, as it were.Examples
No response
Additional context
I think this is the approach that antislop uses.
Acknowledgements