mradermacher/Lingshu-32B-abliterated-GGUF
Quantization (fewer layers) vs drwlf/Lingshu-32B-abliterated. mradermacher/Lingshu-32B-abliterated-GGUF matches part of drwlf/Lingshu-32B-abliterated (771 of its 1161 tensors; the rest of drwlf/Lingshu-32B-abliterated has no counterpart). On the shared part: mradermacher/Lingshu-32B-abliterated-GGUF is a GGUF quantization (Q8_0) of the same weights: 321 tensors match exactly and 450 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/448, lm_head 0/1