mradermacher/Webs-Sejong-31B-v7-GGUF
Quantization (fewer layers) vs websfactory/Webs-Sejong-31B-v7. mradermacher/Webs-Sejong-31B-v7-GGUF matches part of websfactory/Webs-Sejong-31B-v7 (772 of its 1188 tensors; the rest of websfactory/Webs-Sejong-31B-v7 has no counterpart). On the shared part: mradermacher/Webs-Sejong-31B-v7-GGUF is a GGUF quantization (Q8_0) of the same weights: 361 tensors match exactly and 411 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/361, MLP 0/180, Attention 0/230