diff options
| author | Kerfuffle <44031344+KerfuffleV2@users.noreply.github.com> | 2023-11-16 19:14:37 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-11-16 19:14:37 -0700 |
| commit | 91f6499393d2d999331fbfdba47a7f8b9f913f0d (patch) | |
| tree | 27caf3ad0b9cec979bb5ed3317b5334bdcd9470c /common/common.cpp | |
| parent | 8da46278e1a57107591653275f8e03a281de94f0 (diff) | |
Respect tokenizer.ggml.add_bos_token value when tokenizing (#4040)
* gguf-py: gguf-dump: Respect --no-tensor flag in JSON mode.
* Respect add_bos_token GGUF metadata value
* gguf-py: Try to fix SpecialVocab giving up too easily for the Nth time
Diffstat (limited to 'common/common.cpp')
| -rw-r--r-- | common/common.cpp | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/common/common.cpp b/common/common.cpp index 6a711420..e119317d 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -1072,6 +1072,12 @@ std::string llama_detokenize_bpe(llama_context * ctx, const std::vector<llama_to return result; } +bool llama_should_add_bos_token(const llama_model * model) { + const int add_bos = llama_add_bos_token(model); + + return add_bos != -1 ? bool(add_bos) : (llama_vocab_type(model) == LLAMA_VOCAB_TYPE_SPM); +} + // // YAML utils // |