AIML-TUDA/LlavaGuard-v1.2-7B-OV

Partial fine-tune vs lmms-lab/llava-onevision-qwen2-7b-ov. Partial change: 88% of the weights changed (attention, lm_head, mlp, norms, other), in 28 of 28 layers.

Tensors changed: Embeddings 0/4, other 1/5, Norms 55/163, MLP 84/188, Attention 196/404, lm_head 1/1

On the Hub · Downloads on Model Pulse