mirror of
https://github.com/onestardao/WFGY.git
synced 2026-04-28 11:40:07 +00:00
Update eval_latency_vs_accuracy.md
This commit is contained in:
parent
27c9327d9f
commit
bdeab6d983
1 changed files with 5 additions and 0 deletions
|
|
@ -16,6 +16,11 @@
|
|||
> If you need the full triage and all prescriptions, return to the Emergency Room lobby.
|
||||
</details>
|
||||
|
||||
> **Evaluation disclaimer (latency vs accuracy)**
|
||||
> The trade off curves and numbers here depend on your stack, load and datasets.
|
||||
> Treat them as shapes to look for, not fixed targets that prove one model or setting is always better.
|
||||
|
||||
---
|
||||
|
||||
This page defines how to measure, report, and optimize the trade-off between model latency and retrieval/answer accuracy. It is not enough to chase precision; stable systems must also meet latency SLOs while holding ΔS and λ within guardrails.
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue