KKHYA/llavaqwen3-1.7b-finetune-nm-mask-moe-sparse-4e-2k-4of8-impinit-lr5e-4-sd3_20260812_063335

Upload KKHYA/llavaqwen3-1.7b-finetune-nm-mask-moe-sparse-4e-2k-4of8-impinit-lr5e-4-sd3_20260812_063335

Model save

Training in progress, step 5198

initial commit