diff options
| author | staviq <staviq@gmail.com> | 2023-10-17 17:11:01 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-10-17 18:11:01 +0300 |
| commit | 1a159553f921a9209fed8c714494e57b3649f232 (patch) | |
| tree | b880614b6be6541d1890db725a7292fccef93855 /common/train.cpp | |
| parent | 281ef73c258cc1eebec8a64264240432d5878c4b (diff) | |
tokenizer : special token handling (#3538)
* Rewrite special token handling from #1931
* shorten param name, add st verification by type
* use offsets instead of copy by substr
* formatting, remove copying iterator on delete
* llama : normalize code-style
* swift fix
* print pfx/sfx if verb, main: split pfx input sfx
* dont add space when using special tokens
* minor : comment + spacing
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'common/train.cpp')
| -rw-r--r-- | common/train.cpp | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/common/train.cpp b/common/train.cpp index 35a4cf9e..972eaefe 100644 --- a/common/train.cpp +++ b/common/train.cpp @@ -863,7 +863,7 @@ size_t tokenize_file( (int) buf.size(), out_tokens.data(), (int) out_tokens.size(), - false); + false, false); if (n_tokens < 0) { out_tokens.resize(-n_tokens); n_tokens = llama_tokenize( @@ -872,7 +872,7 @@ size_t tokenize_file( (int) buf.size(), out_tokens.data(), (int) out_tokens.size(), - false); + false, false); } if (n_tokens >= 0) { out_tokens.resize(n_tokens); @@ -966,7 +966,7 @@ size_t tokenize_file( (int) buf_sample.size(), tok_sample.data(), (int) tok_sample.size(), - false); + false, false); if (n_tokens < 0) { tok_sample.resize(-n_tokens); n_tokens = llama_tokenize(llama_get_model(lctx), @@ -974,7 +974,7 @@ size_t tokenize_file( (int) buf_sample.size(), tok_sample.data(), (int) tok_sample.size(), - false); + false, false); GGML_ASSERT(n_tokens >= 0); } GGML_ASSERT(n_tokens <= (int) tok_sample.size()); |