seamon67/Supertron-2-Reranker-8B-GGUF
Quantization (fewer layers) vs Surpem/Supertron2-Reranker-8B. seamon67/Supertron-2-Reranker-8B-GGUF matches part of Surpem/Supertron2-Reranker-8B (398 of its 750 tensors; the rest of Surpem/Supertron2-Reranker-8B has no counterpart). On the shared part: seamon67/Supertron-2-Reranker-8B-GGUF is a GGUF quantization (Q8_0) of the same weights: 145 tensors match exactly and 253 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144