manu02/zembed-1-bnb-4bit-nf4-dq
Quantization vs zeroentropy/zembed-1-embedding. manu02/zembed-1-bnb-4bit-nf4-dq is a quantized version of the other (U8/BF16).
Quantization vs zeroentropy/zembed-1-embedding. manu02/zembed-1-bnb-4bit-nf4-dq is a quantized version of the other (U8/BF16).