Scale Bought the Base
8B versus 14B was a controlled comparison. 32B was a fit-on-40GB experiment. Neither scale won the adapter.
Index / term
Adapters
The Mask Is the Objective
Three Qwen3 tool-calling masks: all assistant turns, first call without a terminator, then the terminator—and only the last one worked.
The Loss Is Not the Task
A 50-step math adapter beat a 600-step one, and ViT-Large was best after one epoch—on a single Colab A100.