arianraje/mimo-7b-mamba2-hybrid-init
Same weights, repacked vs XiaomiMiMo/MiMo-7B-RL-0530. Same weights in different files (re-saved, re-sharded or new metadata), plus 216 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/63, lm_head 0/1