TIGER-Lab/EditReward-MiMo-VL-7B-SFT-2508

Full fine-tune vs XiaomiMiMo/MiMo-VL-7B-SFT-2508. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Norms 44/138, MLP 304/304, Attention 380/380, Embeddings 1/1

On the Hub · Downloads on Model Pulse