samithaj
/

GLM-4.7-Flash-MTP-bf16

glm4_moe_lite_mtp

speculative-decoding

multi-token-prediction

Model card Files Files and versions

GLM-4.7-Flash-MTP-bf16

Commit History

Add GLM-4.7-Flash MTP drafter (split via mlx-vlm glm4_moe_lite_mtp)

4256213
verified

samithaj commited on 4 days ago

initial commit

f55e83a
verified

samithaj commited on 4 days ago