Dontopedia

10m Param Model

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

10m Param Model has 4 facts recorded in Dontopedia across 3 references.

4 facts·4 predicates·3 sources

Mostly:can be shifted by rl(1), part of(1), rdf:type(1)

Maturity scale raw canonical shape-checked rule-derived certified

Inbound mentions (3)

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.

affectsAffects(1)

hurtsPerformanceOfHurts Performance of(1)

suggestsScalingExperimentSuggests Scaling Experiment(1)

Other facts (4)

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.

4 facts
PredicateValueRef
Can Be Shifted by RlMeaningfully[1]
Part ofOur Setup[2]
Rdf:typeModel[3]
Has Parameter Count10000000[3]

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.

canBeShiftedByRlblah/vidya/part-7
ex:meaningfully
partOfblah/watt-activation/part-41
ex:our-setup
typeblah/watt-activation/41
ex:Model
hasParameterCountblah/watt-activation/41
10000000

References (3)

3 references
  1. [1]Part 71 fact
    ctx:discord/blah/vidya/part-7
  2. [2]Part 411 fact
    ctx:discord/blah/watt-activation/part-41
  3. [3]412 facts
    ctx:discord/blah/watt-activation/41
    • full textwatt-activation-41
      text/plain2 KBdoc:agent/watt-activation-41/72feaad1-da4d-405f-9a39-dc01405b6065
      Show excerpt
      [2026-03-07 04:39] xenonfun: ### Validation Perplexity: The gold standard for "best" tracking is eval loss on a held-out set — data the model never trains on. You periodically pause, run the model over the val set with no gradient upda

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.