QM60

@turboderp in that graph, "Base" is the base model, right? So the perplexity gap between RoPE and Base is likely due to finetuning on a different dataset. kaiokendev also released...

For what it's worth, I've noticed output quality issues as well in Kobold, which I assumed was related to the sampling swap. However, I noticed similar issues with ooba's very...

Seen it in both, but it's happening constantly in ooba, every other reply. It's very weird. It manifests in a few ways: just forgetting to finish (`doesn'`) finishing with a...