diff options
author | jaime-m-p <167997752+jaime-m-p@users.noreply.github.com> | 2024-06-18 18:40:52 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-06-18 18:40:52 +0200 |
commit | 37bef8943312d91183ff06d8f1214082a17344a5 (patch) | |
tree | 7713dc5aceb3b181568db3d21b1383762de41c4a /ggml-sycl/mmq.cpp | |
parent | 91c188d6c296bd3384f2a02a83b71187aa3d18b3 (diff) |
tokenizer : BPE fixes (#7530)
* Random test: add_bos_token, add_eos_token
* Random test: add BPE models for testing
* Custom regex split fails with codepoint 0
* Fix falcon punctuation regex
* Refactor llm_tokenizer_bpe: move code to constructor
* Move 'add_special_bos/eos' logic to llm_tokenizer_bpe
* Move tokenizer flags to vocab structure.
* Default values for special_add_bos/eos
* Build vocab.special_tokens_cache using vocab token types
* Generalize 'jina-v2' per token attributes
* Fix unicode whitespaces (deepseek-coder, deepseek-llm)
* Skip missing byte tokens (falcon)
* Better unicode data generation
* Replace char32_t with uint32_t
Diffstat (limited to 'ggml-sycl/mmq.cpp')
0 files changed, 0 insertions, 0 deletions