mradermacher/SenseNova-MARS-32B-GGUF
Quantization (fewer layers) vs sensenova/SenseNova-MARS-32B. mradermacher/SenseNova-MARS-32B-GGUF matches part of sensenova/SenseNova-MARS-32B (707 of its 1058 tensors; the rest of sensenova/SenseNova-MARS-32B has no counterpart). On the shared part: mradermacher/SenseNova-MARS-32B-GGUF is a GGUF quantization (Q8_0) of the same weights: 257 tensors match exactly and 450 within quantization error.
Tensors changed: Attention 0/256, Norms 0/257, MLP 0/192, Embeddings 0/1, lm_head 0/1