Clarification on Menlo/Lucy-128k training origin
#2
by
dqdw - opened
Dear [Developer/Team],
Thanks for releasing Menlo/Lucy-128k. I've been experimenting with it and it works well.
Before building on top of it, I would like to understand its connection with Qwen/Qwen3-1.7B:
Direct Fine-tuning: Was Qwen/Qwen3-1.7B the direct starting point for training Menlo/Lucy-128k?
Inheritance: Was there any merging or distillation involved?
Understanding this will help me ensure compatibility with the Qwen/Qwen3-1.7B ecosystem.
Appreciate your support!