it needs a stronger uncensor
#1
by
zekses
- opened
This comment has been hidden
can you post what the exact phrasing of the refusal you got was?
This comment has been hidden
yeah, we are happy with the minimal censors that the model contains. the model is mainly for uncensored programming responses; i.e. programming tasks where the ordinary qwen2.5 coder would provide a refusal such as opsec tasks and whitehat hacking.