-
Notifications
You must be signed in to change notification settings - Fork 198
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
1 changed file
with
1 addition
and
1 deletion.
There are no files selected for viewing
Submodule openvino_tokenizers
updated
27 files
+2 −0 | .github/workflows/labeler.yml | |
+16 −5 | .github/workflows/linux.yml | |
+5 −1 | .github/workflows/mac.yml | |
+5 −2 | .github/workflows/windows.yml | |
+13 −4 | CMakeLists.txt | |
+169 −126 | README.md | |
+4 −3 | pyproject.toml | |
+11 −0 | python/openvino_tokenizers/constants.py | |
+9 −1 | python/openvino_tokenizers/convert_tokenizer.py | |
+169 −50 | python/openvino_tokenizers/hf_parser.py | |
+1 −17 | python/openvino_tokenizers/tiktoken_parser.py | |
+91 −58 | python/openvino_tokenizers/tokenizer_pipeline.py | |
+52 −7 | python/openvino_tokenizers/utils.py | |
+12 −4 | src/CMakeLists.txt | |
+52 −0 | src/byte_fallback.cpp | |
+36 −0 | src/byte_fallback.hpp | |
+1 −1 | src/icu4c.patch | |
+1 −0 | src/ov_extension.cpp | |
+3 −3 | src/ragged_to_dense.cpp | |
+28 −21 | src/sentence_piece.cpp | |
+2 −0 | src/sentence_piece.hpp | |
+1 −0 | src/tokenizer.hpp | |
+21 −20 | src/vocab_decoder.cpp | |
+47 −1 | tests/conftest.py | |
+1 −1 | tests/pass_rates.json | |
+12,885 −0 | tests/stats.json | |
+115 −69 | tests/tokenizers_test.py |