muzzy/GLM-5.2-FP8-DFlash-GGUF
Same weights, converted vs UCloud-org/GLM-5.2-FP8-DFlash. Same weights stored in another dtype (BF16 → BF16/F32), plus 2 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/21, MLP 0/15, Attention 0/20, lm_head 0/1
Same weights, converted vs UCloud-org/GLM-5.2-FP8-DFlash. Same weights stored in another dtype (BF16 → BF16/F32), plus 2 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/21, MLP 0/15, Attention 0/20, lm_head 0/1