Vladimir Zorin
Vladimir Zorin
Cryfs 0.9.9 Just lost lots of my sensitive data because of this issue. Had cryfs dir mounted, laptop battery was low, so it went to shut down -- and look,...
@turboderp Thank you! `gen_begin_reuse()` works like a charm! And it's pretty exciting to run a 33B model with full context on a 4090 with the crazy speed of ~40 tokens/sec....
Yep, getting the same error when trying to quantize llama2-13B with the latest transformers
@hoelzro Hey, so do hints work or not? =) Judging by the docs they should, but I did not get any hints using the example code...
@hoelzro I'm using the example code from the README in the repo, and hinting does not work =(