llama : add support for Tekken pre-tokenizer (#8579)

* llama : Added support for Tekken pre-tokenizer (#8577)

Removed uneeded `vocab.tokenizer_clean_spaces` assignment

* llama : fix order of pre-tokenizers

* * Tekken pre-tokenizer no longer uses clean_up_tokenization_spaces
* Updated chkhsh for Tekken tokenizer

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Michael Coppola 2024-07-20 09:43:51 -04:00 committed by GitHub
parent 69b9945b44
commit 940362224d
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 18 additions and 0 deletions

View file

@ -92,6 +92,7 @@ extern "C" {
LLAMA_VOCAB_PRE_TYPE_CHATGLM4 = 17,
LLAMA_VOCAB_PRE_TYPE_VIKING = 18,
LLAMA_VOCAB_PRE_TYPE_JAIS = 19,
LLAMA_VOCAB_PRE_TYPE_TEKKEN = 20,
};
// note: these values should be synchronized with ggml_rope