diff options
| author | goerch <jhr.walter@t-online.de> | 2023-09-16 13:41:33 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-09-16 13:41:33 +0200 |
| commit | b08e75baea294e366628b898e85c0bd359b58115 (patch) | |
| tree | 417a1a8e7589567ceedba88771056aee080c8e70 /examples | |
| parent | e6616cf0db2b63189fc34d0076f654af9adecdf8 (diff) | |
Fixing the last deviations from sentencepiece indicated by test-tokenizer-1 (#3170)
* Fix für #2721
* Reenable tokenizer test for LLaMa
* Add `console.cpp` dependency
* Fix dependency to `common`
* Fixing wrong fix.
* Make console usage platform specific
Work on compiler warnings.
* Adapting makefile
* Remove trailing whitespace
* Adapting the other parts of the makefile
* Fix typo.
* Fixing the last deviations from sentencepiece indicated by test-tokenizer-1
* Simplify logic
* Add missing change...
* Fix ugly compiler warning
* llama_tokenize should accept strings containing NUL now
* Adding huichen's test case
Diffstat (limited to 'examples')
| -rw-r--r-- | examples/train-text-from-scratch/train-text-from-scratch.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/examples/train-text-from-scratch/train-text-from-scratch.cpp b/examples/train-text-from-scratch/train-text-from-scratch.cpp index 947aa7ed..59c90c7b 100644 --- a/examples/train-text-from-scratch/train-text-from-scratch.cpp +++ b/examples/train-text-from-scratch/train-text-from-scratch.cpp @@ -965,10 +965,10 @@ int tokenize_file(struct llama_context * lctx, const char * filename, std::vecto buf[size] = '\0'; - int n_tokens = llama_tokenize(lctx, buf.data(), out.data(), out.size(), false); + int n_tokens = llama_tokenize(lctx, buf.data(), buf.size(), out.data(), out.size(), false); if (n_tokens < 0) { out.resize(-n_tokens); - n_tokens = llama_tokenize(lctx, buf.data(), out.data(), out.size(), false); + n_tokens = llama_tokenize(lctx, buf.data(), buf.size(), out.data(), out.size(), false); } GGML_ASSERT(n_tokens >= 0); out.resize(n_tokens); |