Dontopedia

Small Models

From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-19.)

Small Models has 13 facts recorded in Dontopedia across 9 references.

13 facts·13 predicates·9 sources

Mostly:working together in(1), includes(1), outperform large models(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (8)

Other subjects in dontopedia point AT this entity as a value. These are inverse relationships — e.g. "X motherOf this subject" — and answer questions the forward facts can't. Grouped by predicate.

accountsFor90PlusPercentParamsAccounts For90 Plus Percent Params(1)

characterizesModelTrainingCharacterizes Model Training(1)

consideredFurtherWithSmallModelsConsidered Further With Small Models(1)

dominatesInDominates in(1)

hasBiggerWinHas Bigger Win(1)

hasMemberHas Member(1)

hasVariantHas Variant(1)

teleologicallyDesignedForTeleologically Designed for(1)

Other facts (13)

The long tail: predicates that appear too rarely to warrant their own section. Filter or scroll to find a specific one. Each row links to its source.

13 facts
PredicateValueRef
Working Together inAgentic Workflows[1]
Includes4 1 Mini Models[1]
Outperform Large ModelsAgentic Workflows[2]
Are Viable for Further UseBrowser Extension[3]
Buildable in<1M[4]
Subset ofSweep Configs[5]
Are AdvocatedXenonfun[6]
Saving Percent0.25[7]
Dominated byOptimizer[7]
Rdf:typeModel Category[8]
Suitable forGeneral Purpose Nlp Tasks[9]
Is Trained onSmaller Datasets[9]
Is Suitable forGeneral Purpose Nlp[9]

Timeline

Timeline axis is valid_time — when each source says the fact was true in the world, not when Dontopedia learned about it. Retracted rows are kept for provenance; coloured stripes indicate the context kind.

workingTogetherInblah/general/part-62
ex:agentic-workflows
includesblah/general/part-62
ex:4-1-mini-models
outperformLargeModelsblah/general/part-13
ex:agentic-workflows
areViableForFurtherUseblah/resources/part-41
ex:browser-extension
buildableInblah/watt-activation/part-253
<1M
subsetOfblah/watt-activation/part-388
ex:sweep-configs
areAdvocatedblah/watt-activation/part-515
ex:xenonfun
savingPercentblah/watt-activation/part-694
0.25
dominatedByblah/watt-activation/part-694
ex:optimizer
typeblah/resources/41
ex:ModelCategory
suitableForlme/2a578673-5ce7-4f89-8d29-0595b9609db0
ex:general-purpose-nlp-tasks
2023-05-21
isTrainedOnlme/2a578673-5ce7-4f89-8d29-0595b9609db0
ex:smaller-datasets
2023-05-21
isSuitableForlme/2a578673-5ce7-4f89-8d29-0595b9609db0
ex:general-purpose-nlp

References (9)

9 references
  1. [1]Part 622 facts
    ctx:discord/blah/general/part-62
  2. [2]Part 131 fact
    ctx:discord/blah/general/part-13
  3. [3]Part 411 fact
    ctx:discord/blah/resources/part-41
  4. [4]Part 2531 fact
    ctx:discord/blah/watt-activation/part-253
  5. [5]Part 3881 fact
    ctx:discord/blah/watt-activation/part-388
  6. [6]Part 5151 fact
    ctx:discord/blah/watt-activation/part-515
  7. [7]Part 6942 facts
    ctx:discord/blah/watt-activation/part-694
  8. [8]411 fact
    ctx:discord/blah/resources/41
  9. ctx:claims/lme/2a578673-5ce7-4f89-8d29-0595b9609db0
    • full textbeam-chunk
      text/plain22 KBdoc:beam/2a578673-5ce7-4f89-8d29-0595b9609db0
      Show excerpt
      [Session date: 2023/05/21 (Sun) 15:59] User: I'm trying to work on a project that involves text analysis and sentiment analysis. Can you recommend some popular NLP libraries in Python that I can use for this project? By the way, I've been b

See also

Keep researching

Missing something or suspicious of what's here? Kick off a research session — a Claude agent will investigate, cite its sources, and file new facts into a dedicated context you can review before accepting into the shared view.