mirror of
https://github.com/ollama/ollama.git
synced 2026-04-17 21:54:08 +02:00
* tokenizer: add byte fallback for SentencePiece BPE encoding When BPE merging produces tokens not in the vocabulary, fall back to encoding each UTF-8 byte as <0xHH> byte tokens instead of silently dropping the character. Also teach Decode to convert <0xHH> tokens back to raw bytes. Fixes #15229, fixes #15231 * tokenizer fixes