Table 5 reports the 125M, 2.5B-token head-structure ablation. Multi-input/Multi-value (MIS/MVA) has the lowest reported perplexity among the listed patterns; MQA/MCS and MKA/MES are substantially worse despite equal total state size. Parameter-matched multi-head patterns fall between these choices.

Table 5 reports the 125M, 2.5B-token head-structure ablation. Multi-input/Multi-value (MIS/MVA) has the lowest reported perplexity among the listed patterns; MQA/MCS and MKA/MES are substantially worse despite equal total state size. Parameter-matched multi-head patterns fall between these choices. · CiteArk

Measurement results

0/35 assessed

0 supported0 disputed or conflicting35 not assessed

The complete result group stays with its claim. Assessed rows come first; their judgments do not replace the whole-claim conclusion. Expand a row for conditions, sources, and evidence history.

Each row is a measurement with its reported value, latest available observation, and cumulative evidence state.
Reported	Latest observation	Evidence judgment
24 heads	—	Not assessed
1 heads	—	Not assessed
1 heads	—	Not assessed
24 heads	—	Not assessed
24 layers	—	Not assessed
126.5 million parameters	—	Not assessed
11.66 perplexity	—	Not assessed
24 heads	—	Not assessed
1 heads	—	Not assessed
24 heads	—	Not assessed
1 heads	—	Not assessed
24 layers	—	Not assessed

Table 5 reports the 125M, 2.5B-token head-structure ablation. Multi-input/Multi-value (MIS/MVA) has the lowest reported perplexity among the listed patterns; MQA/MCS and MKA/MES are substantially worse despite equal total state size. Parameter-matched multi-head patterns fall between these choices.

Reported and observed measurements

Assessments (0)

Runs (0)

Measurement results