mradermacher/SenseNova-MARS-8B-i1-GGUF
Quantization (fewer layers) vs sensenova/SenseNova-MARS-8B. mradermacher/SenseNova-MARS-8B-i1-GGUF matches part of sensenova/SenseNova-MARS-8B (399 of its 750 tensors; the rest of sensenova/SenseNova-MARS-8B has no counterpart). On the shared part: mradermacher/SenseNova-MARS-8B-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 145 tensors match exactly and 254 within quantization error.
Tensors changed: MLP 0/108, Attention 0/144, Norms 0/145, lm_head 0/1, Embeddings 0/1