diff options
Diffstat (limited to 'src/llama-vocab.cpp')
-rw-r--r-- | src/llama-vocab.cpp | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/src/llama-vocab.cpp b/src/llama-vocab.cpp index 474cbd8c..7bae4fec 100644 --- a/src/llama-vocab.cpp +++ b/src/llama-vocab.cpp @@ -427,6 +427,7 @@ struct llm_tokenizer_bpe { break; case LLAMA_VOCAB_PRE_TYPE_STABLELM2: case LLAMA_VOCAB_PRE_TYPE_QWEN2: + case LLAMA_VOCAB_PRE_TYPE_HUNYUAN: regex_exprs = { // original regex from tokenizer.json // "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+" |