Long generations are cut off in the webui about alpaca-turbo HOT 3 OPEN

can you provide entire transcript

i suspect that this issue is related to windows somehow

actually i have pushed some changes to my fork of llama.cpp i think they might fix the issue

from alpaca-turbo.

There is something weird... when post like a 'medium-size' text.

Immediately see this:

inp( #2) :  inp( #2) :  inp( #2) :  inp( #2) :  inp( #2) :  inp( #2) :  inp( #2)

then the answer...

answer for the question

followed by a loop

### Human: continue
### Assistant: Additionally, ...

I find a bit concerning this behaviour on many new models, where the stream gets unlimited by just these human/assistant loops..

from alpaca-turbo.

This should be fixed in the latest release please check and confirm

from alpaca-turbo.