diff --git a/Cargo.toml b/Cargo.toml
index eee2d1f..2423425 100644
--- a/Cargo.toml
+++ b/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "monarch-butterfly"
-version = "0.4.0"
+version = "0.4.1"
 edition = "2021"
 description = "Proc-Macro unrolled FFTs"
 license = "MIT"
@@ -10,11 +10,12 @@ repository = "https://github.com/michaelciraci/Monarch-Butterfly"
 rust-version = "1.63"
 keywords = ["fft", "dft", "discrete", "fourier", "no_std"]
 categories = ["algorithms", "science"]
+exclude = ["assets/", ".*"]
 
 [dependencies]
 monarch-derive = { path = "crates/monarch-derive" }
-num-complex = "0.4"
-num-traits = { version = "0.2", default-features = false }
+num-complex = { version = "0.4", default-features = false, features = ["libm"] }
+num-traits = { version = "0.2", default-features = false, features = ["libm"] }
 
 [dev-dependencies]
 rustfft = "6.2.0"
diff --git a/README.md b/README.md
index ce9b705..8437648 100644
--- a/README.md
+++ b/README.md
@@ -48,7 +48,7 @@ This library will use all SIMD features your CPU has, assuming `rustc` can compi
 The larger the FFT sizes, the larger speed boost this library will give you.
 
 As an example of AVX512 instructions, here is an example on just an FFT
-of size 128: https://godbolt.org/z/Y58eh1x5a (`Ctrl+F` for "zmm" instructions)
+of size 128: <https://godbolt.org/z/Y58eh1x5a> (`Ctrl+F` for "zmm" instructions)
 
 The FFTs before unrolling are heavily inspired from [RustFFT](https://github.com/ejmahler/RustFFT).
 Credit is given to Elliott Mahler as the RustFFT original author.
diff --git a/crates/monarch-derive/Cargo.toml b/crates/monarch-derive/Cargo.toml
index fb6464a..d164fa1 100644
--- a/crates/monarch-derive/Cargo.toml
+++ b/crates/monarch-derive/Cargo.toml
@@ -1,6 +1,6 @@
 [package]
 name = "monarch-derive"
-version = "0.4.0"
+version = "0.4.1"
 edition = "2021"
 description = "Proc-Macro unrolled FFTs"
 license = "MIT"
@@ -15,6 +15,6 @@ proc-macro = true
 [dependencies]
 quote = "1.0.40"
 syn = "2.0.100"
-num-complex = "0.4"
-num-traits = "0.2"
+num-complex = { version = "0.4", default-features = false, features = ["libm"] }
+num-traits = { version = "0.2", default-features = false, features = ["libm"] }
 num-integer = "0.1"
diff --git a/src/lib.rs b/src/lib.rs
index 466cafb..47e2feb 100644
--- a/src/lib.rs
+++ b/src/lib.rs
@@ -1,51 +1,4 @@
-//! [![Build](https://github.com/michaelciraci/Monarch-Butterfly/actions/workflows/rust.yml/badge.svg)](https://github.com/michaelciraci/Monarch-Butterfly/actions/workflows/rust.yml)
-//! [![unsafe forbidden](https://img.shields.io/badge/unsafe-forbidden-success.svg)](https://github.com/rust-secure-code/safety-dance/)
-//! [![](https://img.shields.io/crates/v/monarch-butterfly)](https://img.shields.io/crates/v/monarch-butterfly)
-//! [![](https://docs.rs/monarch-butterfly/badge.svg)](https://docs.rs/monarch-butterfly/)
-//!
-//! # Monarch Butterfly
-//!
-//! Experimental FFT library where all FFTs are proc-macro generated const-evaluation functions. 
-//! The one requirement is you must know the size of the FFT at compile-time. Knowing the FFT size at
-//! compile time gives immense gains, as the compiler is able unroll the call stack and optimize for
-//! SIMD throughput through function calls.
-//!
-//! This library implements FFTs for both `f32` and `f64` sizes `1-200`. The FFTs are 
-//! auto-generated so this limit could be increased above 200 at the expense of compile time.
-//!
-//! ## Features
-//!
-//! - All functions are auto-generated with proc-macros with unrolled loops
-//! - Zero `unsafe` code
-//! - Completely portable
-//! - Const-evaluation functions
-//!
-//! ## Limitations
-//!
-//! - FFT size must be known at compile time
-//! - By default, only FFTs up to size 200 are generated
-//!
-//! ## Usage
-//! 
-//! The top level functions are [`fft`] and [`ifft`].
-//! 
-//! ```
-//! use monarch_butterfly::*;
-//! use num_complex::Complex;
-//!
-//! let input: Vec<_> = (0..8).map(|i| Complex::new(i as f32, 0.0)).collect();
-//! let output = fft::<8, _, _>(input);
-//! ```
-//! This library will use all SIMD features your CPU has available including AVX512,
-//! assuming you compile with those features (`RUSTFLAGS="-C target-cpu=native" cargo build`).
-//!
-//! The larger the FFT sizes, the larger speed boost this library will give you.
-//!
-//! As an example of AVX512 instructions, here is an example on just an FFT
-//! of size 128: <https://godbolt.org/z/Y58eh1x5a>(`Ctrl+F` for "zmm" instructions)
-//!
-//! The FFTs before unrolling are heavily inspired from [`RustFFT`](<https://github.com/ejmahler/RustFFT>).
-//! Credit is given to Elliott Mahler as the RustFFT original author.
+#![doc = include_str!("../README.md")]
 
 #![allow(clippy::excessive_precision)]
 #![forbid(unsafe_code)]