diff --git a/models/ggml-vocab-baichuan.gguf b/models/ggml-vocab-baichuan.gguf
new file mode 100644
index 000000000..7caaf8239
Binary files /dev/null and b/models/ggml-vocab-baichuan.gguf differ
diff --git a/models/ggml-vocab-bloom.gguf b/models/ggml-vocab-bloom.gguf
new file mode 100644
index 000000000..d055ab21c
Binary files /dev/null and b/models/ggml-vocab-bloom.gguf differ
diff --git a/models/ggml-vocab-gpt-neox.gguf b/models/ggml-vocab-gpt-neox.gguf
new file mode 100644
index 000000000..d312dc48c
Binary files /dev/null and b/models/ggml-vocab-gpt-neox.gguf differ
diff --git a/models/ggml-vocab-refact.gguf b/models/ggml-vocab-refact.gguf
new file mode 100644
index 000000000..81ad46a06
Binary files /dev/null and b/models/ggml-vocab-refact.gguf differ
diff --git a/tests/CMakeLists.txt b/tests/CMakeLists.txt
index 1c73de0a3..1817ee2f5 100644
--- a/tests/CMakeLists.txt
+++ b/tests/CMakeLists.txt
@@ -28,10 +28,14 @@ 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_test_executable(test-tokenizer-1-baichuan test-tokenizer-1-llama.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-baichuan.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_test_executable(test-tokenizer-1-mpt test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-mpt.gguf)
+llama_test_executable(test-tokenizer-1-bloom test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-bloom.gguf)
+llama_test_executable(test-tokenizer-1-gpt-neox test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-gpt-neox.gguf)
+llama_test_executable(test-tokenizer-1-refact test-tokenizer-1-bpe.cpp ${CMAKE_CURRENT_SOURCE_DIR}/../models/ggml-vocab-refact.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