14:54
2026-06-14
discuss.huggingface.co
machine-learning
Removing the embedding from my embedding: a byte transformer with a 0-parameter input layer (25M, single RTX 4070)
A researcher reports that a byte transformer with a zero-parameter input layer (HSL-embedding-zero) performs comparably to learned embeddings across text, image, audio, radar, and lidar modalities, wiโฆ