Open Barafu opened 1 month ago
Alright, but for very extreme cases where the context size is very large, the benchmark prompt may not be long enough to trigger a max context generation.
Thanks. I haven't read the benchmark prompt, but you can probably simply duplicate its definition part. At least for me, duplicating the prompt has little effect on the output.
This is now unlocked in 1.67 release
When using benchmark feature, the actual size of text context is limited by 16284 when the
--contextsize
is set to 16384 or greater. Can it be made to utilise full allowed context for more reliable results?