jeffmeloy/Qwen2.5-7B-olm-v1.0

Partial fine-tune vs Qwen/Qwen2.5-7B. Partial change: 84% of the weights changed (attention, lm_head, mlp, norms), in 25 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 49/57, MLP 75/84, Attention 175/196, lm_head 1/1

2 derivatives checked