Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Move headers from include/ to include/pytorch/tokenizers/ #20

Merged
merged 1 commit into from
Feb 14, 2025
+40 −40
Merged

Move headers from include/ to include/pytorch/tokenizers/ #20

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
0 include/base64.h → include/pytorch/tokenizers/base64.h
View file
Open in desktop
File renamed without changes.
4 changes: 2 additions & 2 deletions include/detail/bpe_tokenizer_base.h → ...e/pytorch/tokenizers/bpe_tokenizer_base.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,8 +21,8 @@
#include <re2/re2.h>

// Local
#include "result.h"
#include "tokenizer.h"
#include <pytorch/tokenizers/result.h>
#include <pytorch/tokenizers/tokenizer.h>

namespace tokenizers {
namespace detail {
Expand Down
2 changes: 1 addition & 1 deletion include/error.h → include/pytorch/tokenizers/error.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,8 +13,8 @@

#pragma once

#include <pytorch/tokenizers/log.h>
#include <stdint.h>
#include "log.h"

namespace tokenizers {

Expand Down
10 changes: 5 additions & 5 deletions include/hf_tokenizer.h → include/pytorch/tokenizers/hf_tokenizer.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,11 +19,11 @@
#include <re2/re2.h>

// Local
#include "detail/bpe_tokenizer_base.h"
#include "error.h"
#include "pre_tokenizer.h"
#include "result.h"
#include "token_decoder.h"
#include <pytorch/tokenizers/bpe_tokenizer_base.h>
#include <pytorch/tokenizers/error.h>
#include <pytorch/tokenizers/pre_tokenizer.h>
#include <pytorch/tokenizers/result.h>
#include <pytorch/tokenizers/token_decoder.h>

namespace tokenizers {
class HFTokenizer : public detail::BPETokenizerBase {
Expand Down
2 changes: 1 addition & 1 deletion include/llama2c_tokenizer.h → ...de/pytorch/tokenizers/llama2c_tokenizer.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,8 @@
*/
// @lint-ignore-every CLANGTIDY facebook-hte-RelativeInclude
#pragma once
#include <pytorch/tokenizers/tokenizer.h>
#include <memory>
#include "tokenizer.h"

namespace tokenizers {

Expand Down
1 change: 1 addition & 0 deletions include/log.h → include/pytorch/tokenizers/log.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@

#include <cstdarg>
#include <cstddef>
#include <cstdint>
#include <cstdio>
#include <cstdlib>

Expand Down
0 include/pre_tokenizer.h → include/pytorch/tokenizers/pre_tokenizer.h
View file
Open in desktop
File renamed without changes.
2 changes: 1 addition & 1 deletion include/result.h → include/pytorch/tokenizers/result.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,10 +13,10 @@

#pragma once

#include <pytorch/tokenizers/error.h>
#include <cassert>
#include <new>
#include <utility>
#include "error.h"

namespace tokenizers {

Expand Down
2 changes: 1 addition & 1 deletion include/sentencepiece.h → include/pytorch/tokenizers/sentencepiece.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,10 +10,10 @@
// A tokenizer that works with sentencepiece. Used by Llama2.
#pragma once

#include <pytorch/tokenizers/tokenizer.h>
#include <memory>
#include <vector>
#include "sentencepiece_processor.h"
#include "tokenizer.h"
namespace tokenizers {

struct TokenIndex {
Expand Down
0 .../llama.cpp-unicode/include/unicode-data.h → ...rd-party/llama.cpp-unicode/unicode-data.h
View file
Open in desktop
File renamed without changes.
0 ...party/llama.cpp-unicode/include/unicode.h → ...s/third-party/llama.cpp-unicode/unicode.h
View file
Open in desktop
File renamed without changes.
6 changes: 3 additions & 3 deletions include/tiktoken.h → include/pytorch/tokenizers/tiktoken.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,9 +17,9 @@
#include "re2/re2.h"

// Local
#include "detail/bpe_tokenizer_base.h"
#include "result.h"
#include "tokenizer.h"
#include <pytorch/tokenizers/bpe_tokenizer_base.h>
#include <pytorch/tokenizers/result.h>
#include <pytorch/tokenizers/tokenizer.h>

namespace tokenizers {

Expand Down
0 include/token_decoder.h → include/pytorch/tokenizers/token_decoder.h
View file
Open in desktop
File renamed without changes.
4 changes: 2 additions & 2 deletions include/tokenizer.h → include/pytorch/tokenizers/tokenizer.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,10 +13,10 @@

#pragma once

#include <pytorch/tokenizers/error.h>
#include <pytorch/tokenizers/result.h>
#include <string>
#include <vector>
#include "error.h"
#include "result.h"

namespace tokenizers {

Expand Down
2 changes: 1 addition & 1 deletion src/bpe_tokenizer_base.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
*/
// @lint-ignore-every LICENSELINT

#include "detail/bpe_tokenizer_base.h"
#include <pytorch/tokenizers/bpe_tokenizer_base.h>

// Standard
#include <inttypes.h>
Expand Down
2 changes: 1 addition & 1 deletion src/hf_tokenizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
*/
// @lint-ignore-every LICENSELINT

#include "hf_tokenizer.h"
#include <pytorch/tokenizers/hf_tokenizer.h>

// Standard
#include <filesystem>
Expand Down
2 changes: 1 addition & 1 deletion src/llama2c_tokenizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
* LICENSE file in the root directory of this source tree.
*/
// @lint-ignore-every CLANGTIDY facebook-hte-RelativeInclude
#include "llama2c_tokenizer.h"
#include <pytorch/tokenizers/llama2c_tokenizer.h>
#include <cstring>

namespace tokenizers {
Expand Down
8 changes: 4 additions & 4 deletions src/pre_tokenizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,10 @@
* This source code is licensed under the BSD-style license found in the
* LICENSE file in the root directory of this source tree.
*/
#include "pre_tokenizer.h"

// Local
#include <pytorch/tokenizers/pre_tokenizer.h>
#include <pytorch/tokenizers/third-party/llama.cpp-unicode/unicode.h>

// Standard
#include <algorithm>
Expand All @@ -15,9 +18,6 @@
// Third Party
#include <nlohmann/json.hpp>

// Local
#include "unicode.h"

using json = nlohmann::json;

namespace tokenizers {
Expand Down
2 changes: 1 addition & 1 deletion src/sentencepiece.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@

// A tokenizer that works with sentencepiece.

#include "sentencepiece.h"
#include <pytorch/tokenizers/sentencepiece.h>
#include <cinttypes>
#include <string>
#include "third_party/absl/strings/str_replace.h"
Expand Down
4 changes: 2 additions & 2 deletions src/tiktoken.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,11 +25,11 @@
limitations under the License.
*************************************************************************/

#include "tiktoken.h"
#include <pytorch/tokenizers/base64.h>
#include <pytorch/tokenizers/tiktoken.h>
#include <cinttypes>
#include <fstream>
#include <limits>
#include "base64.h"
#include "re2/re2.h"

namespace tokenizers {
Expand Down
4 changes: 2 additions & 2 deletions src/token_decoder.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@
*/
// @lint-ignore-every LICENSELINT

#include "token_decoder.h"
#include <pytorch/tokenizers/token_decoder.h>

// Standard
#include <cstdarg>
Expand All @@ -16,7 +16,7 @@
#include <nlohmann/json.hpp>

// Local
#include "unicode.h"
#include <pytorch/tokenizers/third-party/llama.cpp-unicode/unicode.h>

using json = nlohmann::json;

Expand Down
7 changes: 3 additions & 4 deletions targets.bzl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,12 @@ def define_common_targets():
runtime.cxx_library(
name = "headers",
exported_headers = subdir_glob([
("include", "*.h"),
("include", "**/*.h"),
("include", "pytorch/tokenizers/*.h"),
]),
header_namespace = "",
visibility = [
"@EXECUTORCH_CLIENTS",
],
header_namespace = "",
)

runtime.cxx_library(
Expand Down Expand Up @@ -66,7 +65,7 @@ def define_common_targets():
"third-party/llama.cpp-unicode/src/unicode-data.cpp",
],
exported_headers = subdir_glob([
("third-party/llama.cpp-unicode/include", "*.h"),
("include", "pytorch/tokenizers/third-party/llama.cpp-unicode/*.h"),
]),
header_namespace = "",
)
Expand Down
2 changes: 1 addition & 1 deletion test/test_base64.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,7 +6,7 @@
* LICENSE file in the root directory of this source tree.
*/

#include "base64.h"
#include <pytorch/tokenizers/base64.h>
#include "gtest/gtest.h"

namespace tokenizers {
Expand Down
2 changes: 1 addition & 1 deletion test/test_llama2c_tokenizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@
#include <TestResourceUtils/TestResourceUtils.h>
#endif
#include <gtest/gtest.h>
#include "llama2c_tokenizer.h"
#include <pytorch/tokenizers/llama2c_tokenizer.h>

using namespace ::testing;

Expand Down
2 changes: 1 addition & 1 deletion test/test_pre_tokenizer.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
#include <re2/re2.h>

// Local
#include "pre_tokenizer.h"
#include <pytorch/tokenizers/pre_tokenizer.h>

using json = nlohmann::json;
using namespace tokenizers;
Expand Down
2 changes: 1 addition & 1 deletion test/test_sentencepiece.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#include <TestResourceUtils/TestResourceUtils.h>
#endif
#include <gtest/gtest.h>
#include "sentencepiece.h"
#include <pytorch/tokenizers/sentencepiece.h>

namespace tokenizers {

Expand Down
2 changes: 1 addition & 1 deletion test/test_tiktoken.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@
#include <TestResourceUtils/TestResourceUtils.h>
#endif
#include <gtest/gtest.h>
#include "tiktoken.h"
#include <pytorch/tokenizers/tiktoken.h>

using namespace ::testing;

Expand Down
2 changes: 1 addition & 1 deletion third-party/llama.cpp-unicode/src/unicode-data.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,7 +27,7 @@ SOFTWARE.

// generated with scripts/gen-unicode-data.py

#include "unicode-data.h"
#include <pytorch/tokenizers/third-party/llama.cpp-unicode/unicode-data.h>

#include <cstdint>
#include <unordered_map>
Expand Down
4 changes: 2 additions & 2 deletions third-party/llama.cpp-unicode/src/unicode.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,8 +29,8 @@ SOFTWARE.
#define _SILENCE_CXX17_CODECVT_HEADER_DEPRECATION_WARNING
#endif

#include "unicode.h"
#include "unicode-data.h"
#include <pytorch/tokenizers/third-party/llama.cpp-unicode/unicode.h>
#include <pytorch/tokenizers/third-party/llama.cpp-unicode/unicode-data.h>

#include <algorithm>
#include <cassert>
Expand Down