smol models
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-06-06.)
smol models has 17 facts recorded in Dontopedia across 8 references, with 1 live disagreement.
Mostly:rdf:type(3), are trained initially on(1), was initially trained on(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedInbound mentions (9)
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.
appliesToApplies to(2)
- Foxhop Post 2026 03 14 11 35 First
ex:foxhop-post-2026-03-14-11-35-first - Gpu Compute Bound
ex:gpu-compute-bound
commitsToSotaOnHardwareConstraintsCommits to Sota on Hardware Constraints(1)
- Foxhop
ex:foxhop
computeBoundForCompute Bound for(1)
- Gpu
ex:gpu
isComputeBoundForIs Compute Bound for(1)
- Gpu
ex:gpu
plansToMakePlans to Make(1)
- Ajaxdavis
ex:ajaxdavis
predictsFutureOfPredicts Future of(1)
- Foxhop
ex:foxhop
presupposesAvailabilityOfPresupposes Availability of(1)
- Cpu Training
ex:cpu-training
targetsTargets(1)
- Harness for Smol Models
ex:harness-for-smol-models
Other facts (14)
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 |
|---|---|---|
| Rdf:type | Model | [6] |
| Rdf:type | Model Category | [7] |
| Rdf:type | Model Type | [8] |
| Are Trained Initially on | Python Samples | [1] |
| Was Initially Trained on | Python Samples | [1] |
| Belong to | Their | [1] |
| Are Various | We Could Think of | [2] |
| Benefit From | Automated Curriculum | [2] |
| Are Smaller Than | Unsloth | [3] |
| Implicates Democratization of | ML Training | [3] |
| Teleologically Aims at | Accessibility | [3] |
| Slang for Small Models | null | [4] |
| Lacks Established Recipe | Training Recipes | [5] |
| Training Method | trained on some python samples | [6] |
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 (8)
ctx:discord/blah/models/part-4ctx:discord/blah/training-and-evals/part-40ctx:discord/blah/unturf/part-55ctx:discord/blah/unturf/part-67ctx:discord/blah/watt-activation/part-254ctx:discord/blah/models/4- full textmodels-4text/plain3 KB
doc:agent/models-4/3a4353a6-71a5-4167-a6bd-95da5250acaaShow excerpt
[2025-04-06 01:15] lisamegawatts: This is one of the things i wanted to test, need to pick base model then run it against different methods of training and do evaluation [2025-04-06 03:14] traves_theberge: the new llama 4 model is a pretty …
ctx:discord/blah/training-and-evals/40- full texttraining-and-evals-40text/plain2 KB
doc:agent/training-and-evals-40/41e5fbb7-2781-4218-afee-0340e0a6d63bShow excerpt
[2026-03-14 11:12] lisamegawatts: Benchmarking against NEAT underway [2026-03-14 11:13] xenonfun: cooler diagrams still debugging (files: Screenshot_2026-03-14_at_7.13.32_AM.png) [2026-03-14 11:14] xenonfun: well long context wins made this…
ctx:discord/blah/unturf/55- full textunturf-55text/plain3 KB
doc:agent/unturf-55/d02ae65b-68f8-4a34-8542-3d3212befee3Show excerpt
[2026-02-14 22:48] uncloseai [bot]: I've fetched and analyzed the contents of the GitLab repository you provided at https://git.unturf.com/engineering/unturf/uncloseai-cli. The primary domain associated with this repository is git.unturf.co…
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.