maldv/Eva-Mindlink-72b

Full fine-tune vs EVA-UNIT-01/EVA-Qwen2.5-72B-v0.2. Fine-tune: 98% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 1/1, Norms 159/161, MLP 240/240, Attention 560/560, lm_head 0/1

2 derivatives checked