Mungert/PLM-1.8B-Instruct-GGUF
Quantization vs PLM-Team/PLM-1.8B-Instruct. Mungert/PLM-1.8B-Instruct-GGUF is a GGUF quantization (Q4_K) of the same weights: 98 tensors match exactly and 192 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/97, MLP 0/64, Attention 0/128