prithivMLmods/MiMo-V2.6-Distill-Qwen-9B-MLX

Partial fine-tune vs XiaomiMiMo/MiMo-V2.6-Distill-Qwen-9B. Partial change: 0% of the weights changed (norms), in 32 of 32 layers.

Tensors changed: Embeddings 0/1, MLP 0/96, Attention 0/200, Norms 81/105

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse