Add a 0.74 confidence threshold so speculative drafting stops early once the draft model's predicted token probability drops below it, favoring shorter, higher-acceptance draft sequences. |
||
|---|---|---|
| .. | ||
| default.nix | ||
| hardware-configuration.nix | ||
| llama-server.nix | ||
| models.ini | ||
| sound.nix | ||
| wyoming.nix | ||
| xremap.nix | ||