giocom/GLM-4.7-Flash-MTP-GGUF
Same weights, converted vs zai-org/GLM-4.7-Flash. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 12 new tensors.
Tensors changed: Embeddings 0/1, lm_head 0/1, Norms 0/5, MLP 0/4, Attention 0/4
Same weights, converted vs zai-org/GLM-4.7-Flash. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 12 new tensors.
Tensors changed: Embeddings 0/1, lm_head 0/1, Norms 0/5, MLP 0/4, Attention 0/4