cerebras/MiniMax-M2-REAP-162B-A10B

Partial fine-tune vs MiniMaxAI/MiniMax-M2. Partial change: 40% of the weights changed (mlp), in 62 of 62 layers.

Tensors changed: MLP 1491/1501, Attention 0/496, Embeddings 0/1, Norms 0/249, lm_head 0/1

3 derivatives checked