Incredible 🤩

Very good! Just out of sheer curiosity: can you post somewhere the full procedure from the original model to your models?
I don't intend to do it, just to read it and learn.

Llama 3.1 model got their tokenizer_config file modified. We updated them.
GGUF already done will have old chat template inside but they still work properly.

Impressive work! After testing, we found that the 12B model has enormous potential, though it exhibits some hallucinations. I wonder if there are any plans for further iterations, as Nemo indeed provides a solid foundation. I really liked the performance of Lumimaid on 8x7b, and I hope to see a model in the next iteration that can outperform 8x7b while also maintaining cost-effectiveness in terms of inference