retomaton
PyTorch code for the RetoMaton paper: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022)
knn-transformers
PyTorch + HuggingFace code for RetoMaton: "Neuro-Symbolic Language Modeling with Automaton-augmented Retrieval" (ICML 2022), including an implementation of kNN-LM and kNN-MT
@stdlib/math-base-special-floor
Round a double-precision floating-point number toward negative infinity.
@stdlib/math-base-special-roundn
Round a numeric value to the nearest multiple of 10^n.
@stdlib/math-base-special-ceilf
Round a single-precision floating-point number toward positive infinity.
@stdlib/math-base-special-ceil2
Round a numeric value to the nearest power of two toward positive infinity.
math-base-special-ceilsd
Round a numeric value to the nearest number toward positive infinity with N significant figures.
@stdlib/math-base-special-floor10
Round a numeric value to the nearest power of 10 toward negative infinity.
@stdlib/math-base-special-floorsd
Round a numeric value to the nearest number toward negative infinity with N significant figures.
@stdlib/math-base-special-ceil10
Round a numeric value to the nearest power of 10 toward positive infinity.
@stdlib/math-base-special-roundsd
Round a numeric value to the nearest number with N significant figures.
@stdlib/math-base-special-round10
Round a numeric value to the nearest power of 10 on a linear scale.
@stdlib/math-strided-special-smskceil
Round each element in a single-precision floating-point strided array toward positive infinity according to a strided mask array.
@stdlib/math-base-special-floorb
Round a numeric value to the nearest multiple of b^n toward negative infinity.
@stdlib/math-strided-special-dceil
Round each element in a double-precision floating-point strided array toward positive infinity.
@stdlib/math-base-special-round2
Round a numeric value to the nearest power of two on a linear scale.
@stdlib/math-strided-special-smsktrunc
Round each element in a single-precision floating-point strided array toward zero according to a strided mask array.
@stdlib/math-strided-special-dmsktrunc
Round each element in a double-precision floating-point strided array toward zero according to a strided mask array.
@stdlib/math-strided-special-dmskceil
Round each element in a double-precision floating-point strided array toward positive infinity according to a strided mask array.
@stdlib/math-base-special-floor2
Round a numeric value to the nearest power of two toward negative infinity.
@stdlib/math-strided-special-dfloor
Round each element in a double-precision floating-point strided array toward negative infinity.
@stdlib/math-strided-special-sfloor
Round each element in a single-precision floating-point strided array toward negative infinity.
math-strided-special-sceil
Round each element in a single-precision floating-point strided array toward positive infinity.
@stdlib/math-strided-special-smskfloor
Round each element in a single-precision floating-point strided array toward negative infinity according to a strided mask array.
@stdlib/math-base-special-ceilb
Round a numeric value to the nearest multiple of b^n toward positive infinity.
@stdlib/math-strided-special-dmskfloor
Round each element in a double-precision floating-point strided array toward negative infinity according to a strided mask array.
math-strided-special-floor
Round each element in a strided array toward negative infinity.
math-strided-special-ceil
Round each element in a strided array toward positive infinity.
math-base-special-floorf
Round a single-precision floating-point numeric value toward negative infinity.
math-base-special-ceil
Round a double-precision floating-point number toward positive infinity.
math-base-special-round-nearest-even
Round numbers to the nearest even integer with the math-base-special-round-nearest-even library. Ideal for precise numerical computations in JavaScript. 🛠️📊
@stdlib/math-base-special-truncsd
Round a numeric value to the nearest number toward zero with N significant figures.
math-base-special-roundf
Round a single-precision floating-point number to the nearest integer.