mradermacher/Artemis-31B-v1.2-abliterix-GGUF
Quantization (fewer layers) vs kawattaronin/Artemis-31B-v1.2-abliterix. mradermacher/Artemis-31B-v1.2-abliterix-GGUF matches part of kawattaronin/Artemis-31B-v1.2-abliterix (772 of its 1188 tensors; the rest of kawattaronin/Artemis-31B-v1.2-abliterix has no counterpart). On the shared part: mradermacher/Artemis-31B-v1.2-abliterix-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