Comment by RandyOrion
4 months ago
First, this is not an open source / weight release.
Second, it has the problem of non-stoping response.
4 months ago
First, this is not an open source / weight release.
Second, it has the problem of non-stoping response.
What's the best technique to train the model to stop responding? A bit of fine tuning on texts with EOS markers?
I didn't see many papers on solving this problem.
I see non-stop response as a generalization problem because normally every training sample is not of infinite length.
Targeted supervised fine-tuning should work, as long as you have enough samples. However, supervised fine-tuning is not good for generalization.