win10/EVA-QwQ-32B-Preview

Partial fine-tune vs EVA-UNIT-01/EVA-Qwen2.5-32B-v0.2. Partial change: 77% of the weights changed (attention, lm_head, mlp, norms), in 64 of 64 layers.

Tensors changed: Embeddings 0/1, Norms 65/129, MLP 150/192, Attention 318/448, lm_head 1/1

3 derivatives checked

On the Hub · Downloads on Model Pulse