Detaches the models used by each replica for unloading. This method is not thread-safe.

! @brief dump a floating-point number Dump a given floating-point number to output stream @a o. Works internally with @a number_buffer.

Absolute value. See also:** Documentation for [std::fabs](https://en.cppreference.com/w/cpp/numeric/math/fabs). \param arg operand \return absolute va

Raise exception flags. This raises the specified floating point exceptions and also invokes any additional automatic exception handling as configured

! For n != 0, returns k, such that pow10 := 10^(k-1) <= n < 10^k. For n == 0, returns 1 and sets pow10 := 1. */

Nearest integer not greater than half value. See also:** Documentation for [std::floor](https://en.cppreference.com/w/cpp/numeric/math/floor). \param

Classify floating-point value. See also:** Documentation for [std::fpclassify](https://en.cppreference.com/w/cpp/numeric/math/fpclassify). \param arg

Decompress floating-point number. See also:** Documentation for [std::frexp](https://en.cppreference.com/w/cpp/numeric/math/frexp). \param arg number

! For a normalized diyfp w = f * 2^e, this function returns a (normalized) cached power-of-ten c = f_c * 2^e_c, such that the exponent of the product

Returns the default configuration used by this model.

Map true modules to exported name

Returns the source vocabulary size expected by the model.

Returns the target vocabulary size expected by the model.

Returns the vocabulary size expected by the model.