TencentBAC/TBAC-VLR1-3B-preview

Partial fine-tune vs Qwen/Qwen2.5-VL-3B-Instruct. Partial change: 74% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/2, Norms 71/138, MLP 108/304, Attention 251/380

2 derivatives checked