nicoboss/PLM-1.8B-Instruct-non-MLA-GGUF
Same weights, converted vs PLM-Team/PLM-1.8B-Instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/64, Attention 0/128
Same weights, converted vs PLM-Team/PLM-1.8B-Instruct. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/64, Attention 0/128