diff options
| author | Ren Xuancheng <jklj077@users.noreply.github.com> | 2024-05-08 20:06:43 +0800 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-05-08 15:06:43 +0300 |
| commit | 229ffff872f8ad0d21c997d18ee7a23692ae60a0 (patch) | |
| tree | b4c2f055395cc0ccbc2b0ade78da27d429cdb2e1 /tests | |
| parent | 1fd9c1741d864d01cd7ec6d67227b92d7bfabf22 (diff) | |
llama : add BPE pre-tokenization for Qwen2 (#7114)
* Add BPE pre-tokenization for Qwen2.
* minor : fixes
---------
Co-authored-by: Ren Xuancheng <17811943+jklj077@users.noreply.github.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'tests')
| -rw-r--r-- | tests/CMakeLists.txt | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt index 208f0cf7..d409a1d6 100644 --- a/tests/CMakeLists.txt +++ b/tests/CMakeLists.txt @@ -84,6 +84,7 @@ llama_test(test-tokenizer-0 NAME test-tokenizer-0-starcoder ARGS ${CMAKE llama_test(test-tokenizer-0 NAME test-tokenizer-0-gpt-2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-2.gguf) llama_test(test-tokenizer-0 NAME test-tokenizer-0-refact ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.gguf) llama_test(test-tokenizer-0 NAME test-tokenizer-0-command-r ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-command-r.gguf) +llama_test(test-tokenizer-0 NAME test-tokenizer-0-qwen2 ARGS ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-qwen2.gguf) # build test-tokenizer-1-bpe target once and add many tests add_executable(test-tokenizer-1-bpe test-tokenizer-1-bpe.cpp) |