vocab: add gemma4 tokenizer tests, fix edge case (#21534)
* YATF (Yet Another Tokenizer Fix) for Gemma 4. With tests! * Remove unnecessary hash from update script. * minor: move constant
This commit is contained in:
committed by
GitHub
parent
243532e556
commit
0ec191e1d7
@@ -124,6 +124,7 @@ llama_test(test-tokenizer-0 NAME test-tokenizer-0-command-r ARGS ${PROJE
|
||||
llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-coder ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-deepseek-coder.gguf)
|
||||
llama_test(test-tokenizer-0 NAME test-tokenizer-0-deepseek-llm ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-deepseek-llm.gguf)
|
||||
llama_test(test-tokenizer-0 NAME test-tokenizer-0-falcon ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-falcon.gguf)
|
||||
llama_test(test-tokenizer-0 NAME test-tokenizer-0-gemma-4 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gemma-4.gguf)
|
||||
llama_test(test-tokenizer-0 NAME test-tokenizer-0-gpt-2 ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-gpt-2.gguf)
|
||||
llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-bpe ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-bpe.gguf)
|
||||
llama_test(test-tokenizer-0 NAME test-tokenizer-0-llama-spm ARGS ${PROJECT_SOURCE_DIR}/models/ggml-vocab-llama-spm.gguf)
|
||||
|
||||
Reference in New Issue
Block a user