FP4 encoding related

[Tiantian-Han]

neural-compressor/neural_compressor/torch/algorithms/weight_only/utility.py

Line 69 in 4372a76

FP4_E2M1 = [-6.0, -4.0, -3.0, -2.0, -1.5, -1.0, -0.0625, 0, 0.0625, 1.0, 1.5, 2.0, 3.0, 4.0, 6.0]

FP4_BNB = [-12.0, -8.0, -6.0, -4.0, -3.0, -2.0, -0.0625, 0, 0.0625, 2.0, 3.0, 4.0, 6.0, 8.0, 12.0]
FP4_E2M1 = [-6.0, -4.0, -3.0, -2.0, -1.5, -1.0, -0.0625, 0, 0.0625, 1.0, 1.5, 2.0, 3.0, 4.0, 6.0]

Why is FP4_E2M1 like this? How is 0.0625 computed? According to OCP-Spec shouldn't it be 0.5? Is FP4_BNB the result of left shifting FP4_E2M1 one bit? Does it correspond to becoming E3M0?