Open Mihaiii opened 2 weeks ago
Hi Mihai, thanks for the issue report -- I'm currently reworking how the logit downregulation & sampling works. There were some underlying conceptual flaws, but it's a lot more solid now.
I'll look into this issue shortly; I agree setting 0.01 should result in deterministic behaviour.
Hi!
I'm trying to make the output deterministic in preparation for a PR for something else. To isolate the issue, since there's no point to set
so_sample=False
, I'm settingtemperature = 0.01
andslop_phrase_prob_adjustments={"sddsadsadwedqdqw": 0.5},
. My expectation was for this to fallback to the default generate and offer a deterministic output, but this doesn't happen.Example to replicate:
Expected behavior: same output always. Actual behavior: different output from run to run.