llama.cpp/main.cpp at 486ae645fd3eda8b9d7413d5ff34fb65a3e337fb

mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-05-11 11:34:10 +00:00

Files

Gary Linscott 486ae645fd Compute perplexity over prompt (#270 )

* Compute perplexity over prompt

* More accurate perplexity calculation - over all logits in the context window (so 512x more tokens!)

* Output all perplexitiies

* Add timing/ETA

2023-03-21 18:27:42 +02:00

45 KiB

Raw Blame History

View Raw

45 KiB Raw Blame History

45 KiB

Raw Blame History