mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-05-08 01:54:10 +00:00
* 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
22 KiB
22 KiB