mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-26 06:10:29 +01:00
eb34620aec
* Add test-tokenizer-0 to do a few tokenizations - feel free to expand * Added option to convert-pth-to-ggml.py script to dump just the vocabulary * Added ./models/ggml-vocab.bin containing just LLaMA vocab data (used for tests) * Added utility to load vocabulary file from previous point (temporary implementation) * Avoid using std::string_view and drop back to C++11 (hope I didn't break something) * Rename gpt_vocab -> llama_vocab * All CMake binaries go into ./bin/ now
5 lines
257 B
CMake
5 lines
257 B
CMake
set(TEST_TARGET test-tokenizer-0)
|
|
add_executable(${TEST_TARGET} ${TEST_TARGET}.cpp)
|
|
target_link_libraries(${TEST_TARGET} PRIVATE utils)
|
|
add_test(NAME ${TEST_TARGET} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab.bin)
|