menik1126/OVD-Math-1-data-RS-Step800-Historical

Partial fine-tune vs Qwen/Qwen2.5-Math-1.5B. Partial change: 85% of the weights changed (attention, mlp, norms), in 28 of 28 layers.

Tensors changed: Embeddings 0/1, Norms 56/57, MLP 84/84, Attention 196/196

On the Hub · Downloads on Model Pulse