When should a tool-using customer-service agent hand off to a human? Qwen3-4B SFT and GRPO models with all data.
-
JaspinXu/KnowWhenToHandOff-Qwen3-4B-R2
Text Generation • 4B • Updated • 39 • 1 -
JaspinXu/KnowWhenToHandOff-Qwen3-4B-R1
Text Generation • 4B • Updated • 39 • 1 -
JaspinXu/KnowWhenToHandOff-Qwen3-4B-SFT
Text Generation • 4B • Updated • 48 • 1 -
JaspinXu/KnowWhenToHandOff-data
Viewer • Updated • 483 • 622 • 1