Lordvarun23/qwen2.5-vl-3b-mllmu-npo-forget5

Partial fine-tune vs Lordvarun23/qwen2.5-vl-3b-mllmu-ft. Partial change: 74% of the weights changed (attention, mlp, norms), in 36 of 36 layers.

Tensors changed: Embeddings 0/2, Norms 70/138, MLP 108/304, Attention 243/380

On the Hub · Downloads on Model Pulse