I’m struggling to get the 7b models to do something useful, obviously I’m doing something wrong as it appears many people strive for 7b models.
But myself I can not get them to follow instructions, they keep repeating stuff and occasionally they start to converse with themselves.
Does anyone have any pointers what I’m doing wrong?
Llama-2 chat, Mistral, Zephyr, and Open Hermes 2.5 are great 7B models for fine-tuning. I have experimented with these and was able to get great results for summarization, and RAG.