0.2.3

What's Changed

Added support for quantized models. 4-bit and 8-bit are supported using the --q flag.

New Contributors

• @blakejakopovic made their first contribution in #25

Full Changelog: 0.2.2...0.2.3

0.2.2

Full Changelog: 0.2.1...0.2.2

0.2.1

Full Changelog: 0.2.0...0.2.1

0.2.0

Full Changelog: 0.1.9...0.2.0

0.1.9

Full Changelog: 0.1.8...0.1.9

0.1.8

Full Changelog: 0.1.7...0.1.8

0.1.7

What's Changed

• Add new duration predictor by @lucasnewman in #15

Full Changelog: 0.1.6...0.1.7

0.1.6

Full Changelog: 0.1.5...0.1.6

0.1.5

Full Changelog: 0.1.4...0.1.5

0.1.4

Highlights

• Added Euler ODE sampling method for ~40% faster generation. Use the --method parameter to select the euler or midpoint sampler.

Full Changelog: 0.1.3...0.1.4