vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add test for MPT tokenization (#3728)

Browse source 
* Add test for MPT tokenization

* Revert code motion

* Remove unnecessary restriction in test case

* Clarify logic in conversion
This commit is contained in:
goerch 2023-10-22 21:21:42 +02:00 • committed by GitHub
parent 5a42a5f8e8
commit 9e70cc0322
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 21 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

1
tests/CMakeLists.txt
View file

@ -31,6 +31,7 @@ llama_test_executable (test-tokenizer-1-llama test-tokenizer-1-llama.cpp ${CMAKE
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_test_executable(test-tokenizer-1-mpt test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-mpt.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