Dontopedia
Explore

Kv Inp Tensor Size

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

Kv Inp Tensor Size has 7 facts recorded in Dontopedia across 1 reference.

7 facts·7 predicates·1 sources

Mostly:has shape768(1), has shape32(1), has shape t(1)

Maturity scale raw canonical shape-checked rule-derived certified

Has Shape768hasShape768

Has Shape32hasShape32

Has Shape ThasShapeT

Has Shape BhasShapeB

Element CountelementCount

  • 100000000[1]sourceall time · 202

Tensor DimensionstensorDimensions

  • (B, T, 32, 768)[1]sourceall time · 202

Rdf:typerdf:type

Inbound mentions (2)

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.

identifiesRootCauseIdentifies Root Cause(1)

operatesOnOperates on(1)

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.

elementCountblah/watt-activation/202
100000000
hasShape32blah/watt-activation/202
ex:feature-dimension-32
hasShape768blah/watt-activation/202
ex:feature-dimension-768
hasShapeBblah/watt-activation/202
ex:batch-dimension
hasShapeTblah/watt-activation/202
ex:time-dimension
typeblah/watt-activation/202
ex:Bottleneck
tensorDimensionsblah/watt-activation/202
(B, T, 32, 768)

References (1)

1 references
  1. customctx:discord/blah/watt-activation/202
    • full textwatt-activation-202
      text/plain3 KBdoc:agent/watt-activation-202/bfa1acbb-7492-43ef-befc-99b62acad42a
      Show excerpt
      [2026-03-10 06:54] xenonfun: ``` lohe_spherical+lohe_v2 summary: train loss (last 50): 7.8510 ppl=2568.3 val loss (final): 7.8019 ppl=2445.1 sys_r @1000: 0.8817 global_r @1000: 0.2008 attn_r @1000:

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.