QiZishi/OphVLM-R1

Partial fine-tune vs OpenGVLab/InternVL3_5-2B. Partial change: 73% of the weights changed (attention, lm_head, mlp, norms), in 28 of 28 layers.

Tensors changed: lm_head 1/1, Embeddings 0/5, Norms 98/209, MLP 84/186, Attention 112/208, other 0/48

On the Hub · Downloads on Model Pulse