embedding-free

Here are 2 public repositories matching this topic...

PyTorch transformer input from raw bytes with zero learned input parameters: no tokenizer, embedding table, or learned input projection.

pytorch hsl byte-level efficient-ai tokenizer-free zero-parameter embedding-free

Language-model proof of operation for HSL's zero-learned-parameter input path. Open code, weights, and documented limitations; not a SOTA claim.

research pytorch hsl language-model byte-level tokenizer-free embedding-free

To associate your repository with the embedding-free topic, visit your repo's landing page and select "manage topics."