mxbai-rerank-large-v1-onnx-quant / quantize_config.json
calmodovar23's picture
Initial commit
24d59fb verified
raw
history blame
1.24 kB
{
"per_channel": true,
"reduce_range": true,
"per_model_config": {
"model": {
"op_types": [
"Ceil",
"Transpose",
"Abs",
"GatherElements",
"Sign",
"Unsqueeze",
"Pow",
"Log",
"Erf",
"Shape",
"Softmax",
"Div",
"Squeeze",
"Expand",
"Constant",
"Sqrt",
"Gemm",
"Less",
"ConstantOfShape",
"Range",
"Clip",
"LessOrEqual",
"MatMul",
"ReduceMean",
"Identity",
"Where",
"Gather",
"Greater",
"Neg",
"Equal",
"Concat",
"Add",
"Slice",
"Mul",
"Tile",
"Cast",
"Reshape",
"And",
"Sub"
],
"weight_type": "QInt8"
}
}
}