cerebras/MiniMax-M2.5-REAP-172B-A10B

Partial fine-tune vs MiniMaxAI/MiniMax-M2.5. Partial change: 42% of the weights changed (mlp), in 62 of 62 layers.

Tensors changed: MLP 1582/1594, Attention 0/496, Embeddings 0/1, Norms 0/249, lm_head 0/1

3 derivatives checked