Draft models for the DCore paper (Qwen3-4B target). Paper: https://arxiv.org/abs/2610.24993
-
wingchiuloong/DCore-Qwen3-4B-Budget8
Text Generation • 0.5B • Updated • 8 • 1 -
wingchiuloong/DCore-Qwen3-4B-Budget16
Text Generation • 0.5B • Updated • 7 • 1 -
wingchiuloong/DCore-DFlash-Qwen3-4B-Budget8
Text Generation • 0.5B • Updated • 6 -
wingchiuloong/DCore-DFlash-Qwen3-4B-Budget16
Text Generation • 0.5B • Updated • 7