mradermacher/Mero-Artemis-31B-v0.3.1-heretic-GGUF
Quantization (fewer layers) vs sh0ck0r/Mero-Artemis-31B-v0.3.1-heretic. mradermacher/Mero-Artemis-31B-v0.3.1-heretic-GGUF matches part of sh0ck0r/Mero-Artemis-31B-v0.3.1-heretic (772 of its 1188 tensors; the rest of sh0ck0r/Mero-Artemis-31B-v0.3.1-heretic has no counterpart). On the shared part: mradermacher/Mero-Artemis-31B-v0.3.1-heretic-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