djuna-test-lab/TEST-Q2.5-AA

Partial fine-tune vs EVA-UNIT-01/EVA-Qwen2.5-7B-v0.1. Partial change: 73% of the weights changed (attention, mlp, norms), in 24 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 48/57, MLP 72/84, Attention 168/196, lm_head 0/1

On the Hub · Downloads on Model Pulse