DevQuasar/openbmb.MiniCPM4.1-8B-GGUF
Same weights, converted vs openbmb/MiniCPM4.1-8B. Same weights stored in another dtype (BF16 → F16/F32), plus 2 new tensors.
Tensors changed: MLP 0/96, Attention 0/128, Norms 0/65, Embeddings 0/1, lm_head 0/1
Same weights, converted vs openbmb/MiniCPM4.1-8B. Same weights stored in another dtype (BF16 → F16/F32), plus 2 new tensors.
Tensors changed: MLP 0/96, Attention 0/128, Norms 0/65, Embeddings 0/1, lm_head 0/1