KKHYA/llavaqwen3-1.7b-finetune-nm-mask-moe-sparse-4e-2k-4of8-imp-anchor_20260812_071057

Partial fine-tune vs KKHYA/llavaqwen3-1.7b-finetune. Partial change: 0% of the weights changed (other), in 0 of 28 layers.

Tensors changed: lm_head 0/1, Embeddings 0/4, Norms 0/213, MLP 0/138, Attention 0/304, other 4/4

On the Hub · Downloads on Model Pulse