Small Models
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-19.)
Small Models has 13 facts recorded in Dontopedia across 9 references.
Mostly:working together in(1), includes(1), outperform large models(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound 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)
- Decoder
ex:decoder
characterizesModelTrainingCharacterizes Model Training(1)
- Black Magic
ex:black-magic
consideredFurtherWithSmallModelsConsidered Further With Small Models(1)
- Lisamegawatts
ex:lisamegawatts
dominatesInDominates in(1)
- Dispatch Overhead
ex:dispatch-overhead
hasBiggerWinHas Bigger Win(1)
- Angle 1
ex:angle-1
hasMemberHas Member(1)
- Spacy Language Models
ex:spacy-language-models
hasVariantHas Variant(1)
- Spacy Language Models
ex:spacy-language-models
teleologicallyDesignedForTeleologically Designed for(1)
- Kuramoto Energy Minimizer
ex:kuramoto-energy-minimizer
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.
| Predicate | Value | Ref |
|---|---|---|
| Working Together in | Agentic Workflows | [1] |
| Includes | 4 1 Mini Models | [1] |
| Outperform Large Models | Agentic Workflows | [2] |
| Are Viable for Further Use | Browser Extension | [3] |
| Buildable in | <1M | [4] |
| Subset of | Sweep Configs | [5] |
| Are Advocated | Xenonfun | [6] |
| Saving Percent | 0.25 | [7] |
| Dominated by | Optimizer | [7] |
| Rdf:type | Model Category | [8] |
| Suitable for | General Purpose Nlp Tasks | [9] |
| Is Trained on | Smaller Datasets | [9] |
| Is Suitable for | General 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.
References (9)
ctx:discord/blah/general/part-62ctx:discord/blah/general/part-13ctx:discord/blah/resources/part-41ctx:discord/blah/watt-activation/part-253ctx:discord/blah/watt-activation/part-388ctx:discord/blah/watt-activation/part-515ctx:discord/blah/watt-activation/part-694ctx:discord/blah/resources/41ctx:claims/lme/2a578673-5ce7-4f89-8d29-0595b9609db0- full textbeam-chunktext/plain22 KB
doc:beam/2a578673-5ce7-4f89-8d29-0595b9609db0Show 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.