well not that much speed up 46K now peak, think its memory bound already.
From Dontopedia, the open, paraconsistent wiki. (Last updated 2026-07-01.)
well not that much speed up 46K now peak, think its memory bound already. has 13 facts recorded in Dontopedia across 1 reference, with 2 live disagreements.
Mostly:mentions(8), quoted as saying(2), rdf:type(1)
Maturity scale
raw canonical shape-checked rule-derived certifiedQuoted As Sayingin disputequotedAsSaying
Inbound 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.
attestedByAttested by(7)
- Anchorkan Output Sample
ex:anchorkan-output-sample - Memory Bound State
ex:memory-bound-state - Model Attention Observation 100k
ex:model-attention-observation-100k - Model Lopsidedness Assertion
ex:model-lopsidedness-assertion - Model Output Observation 8k
ex:model-output-observation-8k - Peak State
ex:peak-state - Spectral Output Sample
ex:spectral-output-sample
isInSourceIs in Source(1)
- Code Block
ex:code-block
Other facts (10)
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 |
|---|---|---|
| Mentions | Model | [1] |
| Mentions | Vocab Size 46k | [1] |
| Mentions | Vocab Size 8k | [1] |
| Mentions | Vocab Size 100k | [1] |
| Mentions | Training Context Same | [1] |
| Mentions | Smoketests | [1] |
| Mentions | Spectral | [1] |
| Mentions | Anchor Kan | [1] |
| Rdf:type | Text Segment | [1] |
| Contains | Code Block | [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.
References (1)
ctx:claims/document/019a8f6a-d43b-40ba-afc1-247f4b73c3a5- full textxenonfun: well not that much speed up 46K now peak, think its memory bound already. 8K voctext/plain680 B
discord:msg/a3126764-fdd1-42f8-9653-a5170ea5bdefShow excerpt
xenonfun: well not that much speed up 46K now peak, think its memory bound already. 8K vocab is signifigantly worse output at same training but makes sense, model was too lopsided with that much embeddings, but at 100K it did observe intere…
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.