Query about Base Model
#1
by Tangchiu - opened
Hi WiroAI,
I found this model wonderful, and thanks so much for sharing it!
As I am setting up my inference environment, could you please confirm if this is a direct LoRA fine-tune of Qwen/Qwen2.5-Math-1.5B, or if an intermediate full-parameter SFT step was involved? Understanding whether it's a direct descendant or a multi-stage adaptation will help me manage the weight loading and compatibility correctly.
Thanks again for your contribution!
Best regards,
Tangchiu