Is there any information on how Qwen 1.8B compares to Pythia 2.8 and Phi 1.5? Would it be worth it to be llamafied, as CausalLM did with the 14B version?

CausalLM (14B, llamafied) model is experimenting with something similar. These are the stories they can create. In my roleplay session, neural chat put me in the community of gypsy people, and it described their culture and customs like it happens in real life, this is an impressive model from Intel.

The koboldcpp-1.46.1 (from October) says ERROR: Detected unimplemented GGUF Arch. It’s best to get the newest version of the backend.