Stop reason: EOS Token Found

#6
by Shingou - opened

I've read the documentation; but, since I am a relative novice in the area of coding, I am stumped. Please advise on how to resolve the model stopping before completing it reply whilst using LM Studio.

Whether the reply is short, or long, I receive this '''error?'''.

At first it was short replies; then I tweak temperature to slightly higher and Top-p to slightly higher. Then I request a story to be generated. The model produced a coherent and interesting tale on the subject I chose, and then when producing its closing sentence it was interrupted prematurely producing the same message as the subject of this thread.

The model was employed as a chat bot with a social system prompt.

How do I resolve this? Thank you.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment