mirror of
https://github.com/mauriceboe/TREK.git
synced 2026-06-30 18:46:00 +00:00
Maurice
f049229e25
On a GPU-less host the model's prompt-eval time scales with input length and dominates total latency. Booking details sit at the top of a confirmation, so capping the extracted text at 4000 chars (was 8000) roughly halves extraction time (~50s warm for a capable local 7B model) with no loss of fields on real hotel/rental confirmations. Tunable if a long multi-segment itinerary needs more.