liudev/zerank-2-reranker-fp8
Quantization vs zeroentropy/zerank-2-reranker. liudev/zerank-2-reranker-fp8 is a quantized version of the other (F8_E4M3/BF16).
Quantization vs zeroentropy/zerank-2-reranker. liudev/zerank-2-reranker-fp8 is a quantized version of the other (F8_E4M3/BF16).