Large Vocab Inference Command

as donto believed on

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

Large Vocab Inference Command is Large vocab without tokenizer (raw token IDs).

4 facts·4 predicates·1 sources

Mostly:rdf:type(1), uses subcommand(1), uses prompt(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

Predicate	Value	Ref
Rdf:type	Command Invocation	[1]
Uses Subcommand	Infer Kick	[1]
Uses Prompt	The	[1]
Description	Large vocab without tokenizer (raw token IDs)	[1]

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.

4 undated

—

typeblah/watt-activation/483

ex:CommandInvocation

—

usesSubcommandblah/watt-activation/483

ex:infer-kick

—

usesPromptblah/watt-activation/483

The

—

descriptionblah/watt-activation/483

Large vocab without tokenizer (raw token IDs)

References (1)

1 references

[1]4834 facts
ctx:discord/blah/watt-activation/483
- full textwatt-activation-483
  text/plain2 KBdoc:agent/watt-activation-483/ff831d27-b514-4766-9acc-e8bfdd310bbf
  Show excerpt
  [2026-03-22 00:58] xenonfun: ⏺ Good intel. The tokenizer is GPT-2 style BPE with vocab.json + merges.txt. Let me build the Rust port with parallel tokenization and streaming. This is a bigger feature so let me scope it properly: ⏺ This is a…

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.

Large Vocab Inference Command

Other facts (4)

Timeline

References (1)

See also

Keep researching