diff options
author | V3n3RiX <venerix@koprulu.sector> | 2025-04-08 08:43:12 +0100 |
---|---|---|
committer | V3n3RiX <venerix@koprulu.sector> | 2025-04-08 08:43:12 +0100 |
commit | e81d2dd033df3a61b874a9a37f951ca05eead86f (patch) | |
tree | 82bfb1314b75b6c04de41a378a4838b7a18b0d68 /sci-ml | |
parent | 288d9455931660abb6dfa534a78d45c7fb901477 (diff) |
gentoo auto-resync : 08:04:2025 - 08:43:11
Diffstat (limited to 'sci-ml')
-rw-r--r-- | sci-ml/Manifest.gz | bin | 4570 -> 4741 bytes | |||
-rw-r--r-- | sci-ml/datasets/Manifest | 2 | ||||
-rw-r--r-- | sci-ml/datasets/datasets-3.0.2.ebuild | 22 | ||||
-rw-r--r-- | sci-ml/fastcore/Manifest | 3 | ||||
-rw-r--r-- | sci-ml/fastcore/fastcore-1.7.29.ebuild | 20 | ||||
-rw-r--r-- | sci-ml/fastcore/metadata.xml | 11 | ||||
-rw-r--r-- | sci-ml/sentencepiece/Manifest | 2 | ||||
-rw-r--r-- | sci-ml/sentencepiece/sentencepiece-0.2.0-r2.ebuild (renamed from sci-ml/sentencepiece/sentencepiece-0.2.0-r1.ebuild) | 2 | ||||
-rw-r--r-- | sci-ml/tokenizers/Manifest | 2 | ||||
-rw-r--r-- | sci-ml/tokenizers/tokenizers-0.21.1-r1.ebuild (renamed from sci-ml/tokenizers/tokenizers-0.21.1.ebuild) | 46 |
10 files changed, 105 insertions, 5 deletions
diff --git a/sci-ml/Manifest.gz b/sci-ml/Manifest.gz Binary files differindex 094a9cd0be9e..659447130405 100644 --- a/sci-ml/Manifest.gz +++ b/sci-ml/Manifest.gz diff --git a/sci-ml/datasets/Manifest b/sci-ml/datasets/Manifest index 86d43b89b744..4464000e2867 100644 --- a/sci-ml/datasets/Manifest +++ b/sci-ml/datasets/Manifest @@ -1,5 +1,5 @@ AUX datasets-2.21.0-tests.patch 721 BLAKE2B cf85b02a4eb5da27e52bf819f00e333d6e3fb3fb0b9f7279afff24e3fddf76fcd46cb5e06d29b4780d0ce6b48c9378df301c70f6339e2f2898560219ebab4210 SHA512 43cdc5af6ba3fff3e7641006be6d8e10a5ad00136c1cf137628456019cccbd3d05b888b7eeec1cb8cd42d5ce52091b2a66d32a5b41ff2193658c4257900ea45c AUX datasets-3.0.2-tests.patch 335 BLAKE2B b7499d85cc8cf09a2cb9b58aa0c7ab16c1bc700812c767465979cc59b11d63d05f52422ae731317f373314164715079f6fa81b30d47e3058ce88d6539d049789 SHA512 3f533ab765362ea6a1bc7a1766d332f5bc53e342cbb684061eaed58ef415f715c003f210b73a8b0ca20245d8e1f60517191829fb64feb53101211a9f81542e5a DIST datasets-3.0.2.gh.tar.gz 1867037 BLAKE2B 92475ac566bd825c542dbd3e138c83e1733e6d1137f30a2cfd8f82f7dd54ed78c0566aa766182625e8787413be18f5a0c0c0a289b5823fa9112dcb2876074b7e SHA512 aa55dd2f53df7217c30999f759c76a13d78851233bce4df9b1ad85081e101a7280e905822160874d24d15ea1e1a5ecee1bae9cc66785e89af45ad16dd0339595 -EBUILD datasets-3.0.2.ebuild 2612 BLAKE2B cc533351d7685f3e40cd458c324c3a29c51e3cfe7ed0258962793a4d6c4a14c34a12dc142292a0c09f801afeb5125617a2d52d2f41ac36c824fcba72ab09c5d3 SHA512 5d9da157f3e4747c6e21a32678998b64acb364dc5db32dab43a262633f2b6030d762bfbeca044647ef74946dce9588149f6075f28d3072e270621cf49b432221 +EBUILD datasets-3.0.2.ebuild 3719 BLAKE2B 7a92e202696f88610506c73a07b405ef3a7a512c30a0e8d41a7e51ab6b9659dc05e6c750a664a079f53651a8c295340b1cb6643348e21d2ae0252abbca6545e8 SHA512 a0b0180d914c105e0a74a7fd21b6c7c193e9149c9426dd9ec63df662187509f713a8daf4c9b5384dde2b5e6755a9e1f63620e33e5353fee164f285b43577c10a MISC metadata.xml 379 BLAKE2B 48ebb9e7bfa8b58b0d15b82c4146def465e08cf3212ab4af04129d09c153b67b00d0fa05b94d6af54f643ec3a202f2335d3254b966f49d1394d3c7b9e5da56a5 SHA512 99560decfaa0e438980f372d99257695e9ca9585167d9aba091e0b775c2f8384657ddc017841c8f06f8b568017a54fb9e31da736f3c875da717e154cdce876d1 diff --git a/sci-ml/datasets/datasets-3.0.2.ebuild b/sci-ml/datasets/datasets-3.0.2.ebuild index e6b81257061a..0d701b79377a 100644 --- a/sci-ml/datasets/datasets-3.0.2.ebuild +++ b/sci-ml/datasets/datasets-3.0.2.ebuild @@ -69,13 +69,18 @@ src_prepare() { src_test() { local EPYTEST_IGNORE=( tests/features/test_audio.py - tests/test_fingerprint.py tests/packaged_modules/test_audiofolder.py tests/packaged_modules/test_spark.py + tests/test_fingerprint.py tests/test_iterable_dataset.py + tests/test_inspect.py + tests/test_load.py + tests/test_upstream_hub.py ) local EPYTEST_DESELECT=( + tests/commands/test_test.py::test_test_command + tests/io/test_parquet.py::test_parquet_read_geoparquet tests/packaged_modules/test_cache.py::test_cache_multi_configs tests/packaged_modules/test_cache.py::test_cache_single_config tests/test_arrow_dataset.py::BaseDatasetTest::test_filter_caching_on_disk @@ -83,7 +88,22 @@ src_test() { tests/test_distributed.py::test_torch_distributed_run tests/test_file_utils.py::TestxPath::test_xpath_rglob tests/test_file_utils.py::TestxPath::test_xpath_glob + tests/test_file_utils.py::test_xexists_private + tests/test_file_utils.py::test_xlistdir_private + tests/test_file_utils.py::test_xisdir_private + tests/test_file_utils.py::test_xisfile_private + tests/test_file_utils.py::test_xgetsize_private + tests/test_file_utils.py::test_xglob_private + tests/test_file_utils.py::test_xwalk_private tests/test_hub.py::test_convert_to_parquet + tests/packaged_modules/test_cache.py::test_cache_capital_letters + tests/packaged_modules/test_folder_based_builder.py::test_data_files_with_different_levels_no_metadata + tests/packaged_modules/test_folder_based_builder.py::test_data_files_with_one_label_no_metadata + tests/test_data_files.py::test_DataFilesList_from_patterns_locally_with_extra_files + tests/test_data_files.py::test_DataFilesDict_from_patterns_locally_or_remote_hashing + tests/test_file_utils.py::test_xopen_remote + tests/test_hub.py::test_delete_from_hub + tests/test_offline_util.py::test_offline_with_timeout ) distutils-r1_src_test } diff --git a/sci-ml/fastcore/Manifest b/sci-ml/fastcore/Manifest new file mode 100644 index 000000000000..11e97cf87d57 --- /dev/null +++ b/sci-ml/fastcore/Manifest @@ -0,0 +1,3 @@ +DIST fastcore-1.7.29.tar.gz 854672 BLAKE2B dc62bf2a84cde5ee4bd5519dd184008136129b8c06e888f3587e95e29f124aae1a7de7ffbbf64ca63f95f2033dc677bce2d78b18a9acfd4637e05ad31b85c4b3 SHA512 0caf1ceb273a9c4f5b8fd65b5cf29c028be07d2a337b425233fdfd2089e7ce466857935359f321398df9ecdfd6ce8f2d84a681efaf78e5824bce69f884211d4f +EBUILD fastcore-1.7.29.ebuild 520 BLAKE2B 6b459fc2d35f4df95028c41b03390fbf97054b1f9d59585f2e2734eb39c67e492450b38948c4cb799acc79f6a9e39ce7e97aaad44a945e80cbff753be4a94911 SHA512 36426d579278c698e1248f7a41bb96c9a93aa676cffddfd4b12b37056e8a303e7c4e9e61fb2f7c6cec726f055c67a9b8ca77597bfe71676690820d5a5ab957ad +MISC metadata.xml 333 BLAKE2B 5a3c51fd4f3d72ed7b6b9a3ebb633fed354d83b798f84ae9dad01fcb017fe61332e556c111c84b6b4f2c78385b0899f2c32eec50492f527186d7540cbb421634 SHA512 eaeb69885c3bca4dadfddba8ef3cc0482cd6d96cb61662a08d51227f6235bd73b7e2c4d9074dc675a0a1d4bbec278a26a1cee85ac9988c6e6215f58c4eae6784 diff --git a/sci-ml/fastcore/fastcore-1.7.29.ebuild b/sci-ml/fastcore/fastcore-1.7.29.ebuild new file mode 100644 index 000000000000..9ae8d57f581c --- /dev/null +++ b/sci-ml/fastcore/fastcore-1.7.29.ebuild @@ -0,0 +1,20 @@ +# Copyright 2025 Gentoo Authors +# Distributed under the terms of the GNU General Public License v2 + +EAPI=8 +PYTHON_COMPAT=( python3_{11..13} ) +DISTUTILS_USE_PEP517=setuptools +inherit distutils-r1 + +DESCRIPTION="Python supercharged for the fastai library" +HOMEPAGE="https://fastcore.fast.ai/" +SRC_URI="https://github.com/AnswerDotAI/${PN}/archive/refs/tags/${PV}.tar.gz + -> ${P}.tar.gz" + +LICENSE="Apache-2.0" +SLOT="0" +KEYWORDS="~amd64" + +RESTRICT="test" # No test available + +RDEPEND="dev-python/packaging[${PYTHON_USEDEP}]" diff --git a/sci-ml/fastcore/metadata.xml b/sci-ml/fastcore/metadata.xml new file mode 100644 index 000000000000..3d5bcd63f75b --- /dev/null +++ b/sci-ml/fastcore/metadata.xml @@ -0,0 +1,11 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!DOCTYPE pkgmetadata SYSTEM "https://www.gentoo.org/dtd/metadata.dtd"> +<pkgmetadata> + <maintainer type="person"> + <email>tupone@gentoo.org</email> + <name>Tupone Alfredo</name> + </maintainer> + <upstream> + <remote-id type="github">AnswerDotAI/fastcore</remote-id> + </upstream> +</pkgmetadata> diff --git a/sci-ml/sentencepiece/Manifest b/sci-ml/sentencepiece/Manifest index cf18fd18c05c..c48c840cf8c0 100644 --- a/sci-ml/sentencepiece/Manifest +++ b/sci-ml/sentencepiece/Manifest @@ -1,4 +1,4 @@ AUX sentencepiece-0.2.0-gcc15.patch 314 BLAKE2B befcc8bea7b4b9ca518218ecc8cea1857a8e21d123a8e45b14f392effb94537f55e60f8fa5aa13e659d9b8315177b6ddb0558c8577d2838d0c475f1c107e7e21 SHA512 f21684bbeaa91d09f188c72302120a23f02e02fd551a61b47907c0a732b31980ee896625c0dc1101cb571ccc294f7f3e3d39ff45cfced24486bb6a4e8adaa6a8 DIST sentencepiece-0.2.0.tar.gz 11980811 BLAKE2B adf28a66de3f6995d31c3b9be6a324614b95f20fe07ea33dd914bcd9d33d123dfee69f80ef7b2a70c3c23700534916caf57ac877e55e5c9d0d671d37372e0aed SHA512 b4214f5bfbe2a0757794c792e87e7c53fda7e65b2511b37fc757f280bf9287ba59b5d630801e17de6058f8292a3c6433211917324cb3446a212a51735402e614 -EBUILD sentencepiece-0.2.0-r1.ebuild 1011 BLAKE2B bff042d00ecf80d22963a018c416016e239fabef2ebb67351b641b94f80ecb7c7565639f524bd967a6252c6473a79f2e841abe8307f11e9ef6adecc2670202cc SHA512 bc3b3bfa82d70ff0af4b412321a0ab54a0e766f9520197490ffa46d06510c02eab1d2fbaf44a48a486094b2a8b9184a181808a7abb35df96821c01eccf6869c3 +EBUILD sentencepiece-0.2.0-r2.ebuild 1013 BLAKE2B 7aced3287a6ef4fdd7276f6c827437379db1beb65a0a83f574f3ed34c7fa31e81ec078bbe12a8addbce60bf6a1df57d88329f868c01389e1ac1ba8a49211d674 SHA512 6babfeed9a2b67219b9d5c2e66d0f6606caf22ae06e9c9abf5b52f6cc6321baa11e8d6667dc81ee4ca62ba785823a7cd256829b12bbb450f77dd6f195c13fa98 MISC metadata.xml 333 BLAKE2B 03fe2156a6c7e3c777d32eaad0116b47c67929331f479a91eed112aae5740160be79048c0488f124824e079b7e8316efd8b20b27c0f37e99b3fa47fe1c7abcb9 SHA512 b0b545f7110d19388c741d11ec2225526b73f359b50ad9e77757dd741138376f68b18b2130e78c172de2b95c4803b66c7179d6ced8c06d2ddd828fb0262b2c38 diff --git a/sci-ml/sentencepiece/sentencepiece-0.2.0-r1.ebuild b/sci-ml/sentencepiece/sentencepiece-0.2.0-r2.ebuild index 478b86dc42bd..f35cc636641c 100644 --- a/sci-ml/sentencepiece/sentencepiece-0.2.0-r1.ebuild +++ b/sci-ml/sentencepiece/sentencepiece-0.2.0-r2.ebuild @@ -15,7 +15,7 @@ SLOT="0" KEYWORDS="~amd64" RDEPEND=" - dev-cpp/abseil-cpp + dev-cpp/abseil-cpp:= dev-libs/protobuf:= dev-util/google-perftools " diff --git a/sci-ml/tokenizers/Manifest b/sci-ml/tokenizers/Manifest index 532a15a7bbf4..02af9c5f1fb9 100644 --- a/sci-ml/tokenizers/Manifest +++ b/sci-ml/tokenizers/Manifest @@ -425,5 +425,5 @@ DIST zerovec-0.10.4.crate 126398 BLAKE2B b078784d6f178bbb9de1c3c1b6c7ef996f00bdd DIST zerovec-derive-0.10.2.crate 19366 BLAKE2B 226d599e59c682ba167506d9cedf4f1b004881a624cec3b462ae0d2a1982e9297b9943b70649f0e98e46bf6a6fca68952d181625723a5bdcf779f07cf412dba7 SHA512 da4a056e9147142e51a58c3b16a12179433fc889b4efacbadd1294bb5a750860201a472bf7d72a10e7e82e95d97761a67ec93a727620c1c1844a15362f6736ea DIST zerovec-derive-0.10.3.crate 19438 BLAKE2B 9f7df8a4e4a0b62ab25aed967b26509db4bcc5d5b10b3bd73305099a4c49a60be8921484ced1a34d9b7ae30ffa5abe789686f432416a8f1cfc07de1db1dff594 SHA512 caefbffeb35265db9f74933bf07109d57f0da48156cafd4f330af78a5c7eb9ab0831a80789ad4fb119875ebc6cfd7e3de68c9984b77dca5151f9be41f1ae6e09 EBUILD tokenizers-0.21.0.ebuild 10449 BLAKE2B f89504b2574dd40f007b2905550f064baeb4c6fcc24ed851f0bebec156985fccf2f8465f1ba329648028bc4fabc916c0a6b26b6467ec052ecf5367d52b327f63 SHA512 01fa089db5441d006eece40e75ac7a8296ed842865a4288ae534edb6c9c90193f9283d3580171efb898bdd4a12f461c7da71f066eeb18a0ac0bf059f89732827 -EBUILD tokenizers-0.21.1.ebuild 7879 BLAKE2B 1f91c18e6bb066becb837ae1aa89cef3bc39b220b1eb70c9be71d69984bbda2c8ba5ba0a10fa0bf265390209ad9d68d4d75c3b7514a030d26f3c2e1ed13ed0fc SHA512 8d79b1d186c72f3413e5876585f8274c875fc9903ead0ee4d5135de267c5818f986452bd73acf980594c4264a6fd5a4424a77ab32ac8631a0d275a9142f90cb2 +EBUILD tokenizers-0.21.1-r1.ebuild 11151 BLAKE2B bc68865d1a48aa89ce9d2915daa3b231f10b68d20ef798f5e9308509c34f6a09849883dc72b7441e1101c314c9341fb85c88f62c643061deb84767cc404441c0 SHA512 a1d0f1e757d38d5010f4426381179401e3fe3ac23fe0f137dc3e908673762ffa64a280e6562b42927e121e9a5314ae4998dfcbf17c2f9785eb66199c8543714e MISC metadata.xml 335 BLAKE2B 55e4d7b301e4315210bf24a4056741cc923c6a72ae323158c5715fade20db86de8a03464bf8f12fe7116689b41aa0519a0070eebff5f63801e23a9c4a9698a92 SHA512 77f537f495b90ad031842f704c5a629cc995fcd848f11defeb597cc16d2d7bab07d262f05a50b07788d2f58fb60eacbefdfa8328215b89b0c661a05b18c4555d diff --git a/sci-ml/tokenizers/tokenizers-0.21.1.ebuild b/sci-ml/tokenizers/tokenizers-0.21.1-r1.ebuild index 3861fbf55811..9fa219ec5e6e 100644 --- a/sci-ml/tokenizers/tokenizers-0.21.1.ebuild +++ b/sci-ml/tokenizers/tokenizers-0.21.1-r1.ebuild @@ -349,6 +349,7 @@ LICENSE+=" SLOT="0" KEYWORDS="~amd64" +RDEPEND="dev-libs/oniguruma" BDEPEND=" test? ( sci-ml/datasets[${PYTHON_SINGLE_USEDEP}] ) $(python_gen_cond_dep ' @@ -384,6 +385,7 @@ src_configure() { } src_compile() { + export RUSTONIG_SYSTEM_LIBONIG=1 cd tokenizers cargo_src_compile cd ../bindings/python @@ -396,6 +398,50 @@ src_test() { #cargo_src_test cd ../bindings/python local -x EPYTEST_IGNORE=( benches/ ) + local -x EPYTEST_DESELECT=( + tests/bindings/test_encoding.py::TestEncoding::test_sequence_ids + tests/bindings/test_encoding.py::TestEncoding::test_n_sequences + tests/bindings/test_encoding.py::TestEncoding::test_word_to_tokens + tests/bindings/test_encoding.py::TestEncoding::test_word_to_chars + tests/bindings/test_encoding.py::TestEncoding::test_token_to_sequence + tests/bindings/test_encoding.py::TestEncoding::test_token_to_chars + tests/bindings/test_encoding.py::TestEncoding::test_token_to_word + tests/bindings/test_encoding.py::TestEncoding::test_char_to_token + tests/bindings/test_encoding.py::TestEncoding::test_char_to_word + tests/bindings/test_encoding.py::TestEncoding::test_truncation + tests/bindings/test_encoding.py::TestEncoding::test_invalid_truncate_direction + tests/bindings/test_models.py::TestBPE::test_instantiate + tests/bindings/test_models.py::TestWordLevel::test_instantiate + tests/bindings/test_models.py::TestWordPiece::test_instantiate + tests/bindings/test_processors.py::TestByteLevelProcessing::test_processing + tests/bindings/test_trainers.py::TestUnigram::test_continuing_prefix_trainer_mismatch + tests/bindings/test_trainers.py::TestUnigram::test_train + tests/bindings/test_trainers.py::TestUnigram::test_train_parallelism_with_custom_pretokenizer + tests/documentation/test_pipeline.py::TestPipeline::test_pipeline + tests/documentation/test_pipeline.py::TestPipeline::test_bert_example + tests/implementations/test_char_bpe.py::TestCharBPETokenizer::test_basic_encode + tests/implementations/test_char_bpe.py::TestCharBPETokenizer::test_lowercase + tests/implementations/test_char_bpe.py::TestCharBPETokenizer::test_decoding + tests/implementations/test_char_bpe.py::TestCharBPETokenizer::test_multiprocessing_with_parallelism + tests/test_serialization.py::TestSerialization::test_full_serialization_albert + tests/test_serialization.py::TestSerialization::test_str_big + tests/bindings/test_tokenizer.py::TestTokenizer::test_encode_formats + tests/bindings/test_tokenizer.py::TestTokenizer::test_encode_add_special_tokens + tests/bindings/test_tokenizer.py::TestTokenizer::test_from_pretrained + tests/bindings/test_tokenizer.py::TestTokenizer::test_from_pretrained_revision + tests/bindings/test_tokenizer.py::TestTokenizer::test_encode_special_tokens + tests/bindings/test_tokenizer.py::TestTokenizer::test_splitting + tests/documentation/test_quicktour.py::TestQuicktour::test_quicktour + tests/documentation/test_tutorial_train_from_iterators.py::TestTrainFromIterators::test_datasets + tests/documentation/test_tutorial_train_from_iterators.py::TestTrainFromIterators::test_gzip + tests/implementations/test_bert_wordpiece.py::TestBertWordPieceTokenizer::test_basic_encode + tests/implementations/test_bert_wordpiece.py::TestBertWordPieceTokenizer::test_multiprocessing_with_parallelism + tests/implementations/test_byte_level_bpe.py::TestByteLevelBPE::test_basic_encode + tests/implementations/test_byte_level_bpe.py::TestByteLevelBPE::test_add_prefix_space + tests/implementations/test_byte_level_bpe.py::TestByteLevelBPE::test_lowerspace + tests/implementations/test_byte_level_bpe.py::TestByteLevelBPE::test_multiprocessing_with_parallelism + + ) distutils-r1_src_test } |