llama.cpp/examples/perplexity/perplexity.cpp at 3e945cc1e9c06d2001031360e4e303e9548fb02c

mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00

Files

Kawrakow 3e945cc1e9 HellaSwag: speed up by parallelizing log-prob evaluation (#5020 )

For Mistral-7B and fp16, time on my system goes down from 536 seconds
to 423 seconds for the full evaluation dataset (10042 tasks).

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2024-01-18 19:18:21 +02:00

40 KiB

Raw Blame History

View Raw

40 KiB Raw Blame History

40 KiB

Raw Blame History