aether-55m
A masked (absorbing-state) diffusion language model trained with Aether. Unlike an autoregressive model, generation does not proceed left...
A masked (absorbing-state) diffusion language model trained with Aether. Unlike an autoregressive model, generation does not proceed left...
Diffutron is a parameter-efficient, Masked Diffusion Language Model (MDLM) specifically designed for the Turkish language. Unlike standard autoregressive...