llama.cpp/tests/CMakeLists.txt
goerch ff5a3f0c09
Work on the BPE tokenizer (#3252)
* Work on the BPE tokenizer

Tokenizer tests work for Falcon-7B

* Try to fix build problem

* Fix debug assertion failure

* Fix MSVC Unicode BOM problem

* Cleanup and an improvement

* Fix compiler warning

* Cleanup

* Test doesn't work over the full range of Unicodes

* Update .gitignore and Makefile

* Another Makefile rule

* Testing Aquila

* Moving byte decoding back to `token_to_piece` ...

... because everyone is using it.

* Guarding some unusable code pathes

* Streamlining code and adding some more assertions

Important change: I'm classifying added tokens as control tokens now for BPE.

* Adding a comment

* Adding another assertion

* Fixed vocabulary guarding assertions

* Fix PR for recent change

* Fix PR for recent change

* Fix for compiler warning

* Fix PR for recent change

* Fix PR for recent change

* Fix PR for recent change

* Fix for compiler warning

* Fixes for more compiler warnings

* Remove unused code

* Fix initialization of static maps

* Add scores and token types back, adapt gptneox

* Update llama.cpp

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update unicode.h

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update unicode.h

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Ported Starcoder and added some assertions

* Fix coding style

* Apply @jploski 's fix for missing tokens

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2023-10-03 09:16:26 +02:00

45 lines
2.3 KiB
CMake

function(llama_build_executable source)
get_filename_component(TEST_TARGET ${source} NAME_WE)
add_executable(${TEST_TARGET} ${source})
install(TARGETS ${TEST_TARGET} RUNTIME)
target_link_libraries(${TEST_TARGET} PRIVATE llama common)
endfunction()
function(llama_test_executable name source)
get_filename_component(TEST_TARGET ${source} NAME_WE)
add_test(NAME ${name} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${ARGN})
endfunction()
function(llama_build_and_test_executable source)
get_filename_component(TEST_TARGET ${source} NAME_WE)
add_executable(${TEST_TARGET} ${source})
install(TARGETS ${TEST_TARGET} RUNTIME)
target_link_libraries(${TEST_TARGET} PRIVATE llama common)
add_test(NAME ${TEST_TARGET} COMMAND $<TARGET_FILE:${TEST_TARGET}> ${ARGN})
endfunction()
# llama_build_and_test_executable(test-double-float.cpp) # SLOW
llama_build_and_test_executable(test-quantize-fns.cpp)
llama_build_and_test_executable(test-quantize-perf.cpp)
llama_build_and_test_executable(test-sampling.cpp)
llama_build_executable(test-tokenizer-0-llama.cpp)
llama_test_executable (test-tokenizer-0-llama test-tokenizer-0-llama.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama.gguf)
llama_build_executable(test-tokenizer-0-falcon.cpp)
llama_test_executable (test-tokenizer-0-falcon test-tokenizer-0-falcon.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf)
llama_build_executable(test-tokenizer-1-llama.cpp)
llama_test_executable (test-tokenizer-1-llama test-tokenizer-1-llama.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-llama.gguf)
llama_build_executable(test-tokenizer-1-bpe.cpp)
llama_test_executable (test-tokenizer-1-falcon test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-falcon.gguf)
llama_test_executable(test-tokenizer-1-aquila test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-aquila.gguf)
llama_build_and_test_executable(test-grammar-parser.cpp)
llama_build_and_test_executable(test-llama-grammar.cpp)
llama_build_and_test_executable(test-grad0.cpp) # SLOW
# llama_build_and_test_executable(test-opt.cpp) # SLOW
llama_build_and_test_executable(test-rope.cpp)
# dummy executable - not installed
get_filename_component(TEST_TARGET test-c.c NAME_WE)
add_executable(${TEST_TARGET} test-c.c)
target_link_libraries(${TEST_TARGET} PRIVATE llama)