diff --git a/pyproject.toml b/pyproject.toml index e06a94a..ba8099e 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -11,7 +11,7 @@ readme = "README.md" requires-python = "==3.12.11" dependencies = [ "faiss-cpu==1.8.0", - "transformers==4.44.2", + "transformers==4.57.1", "torch==2.4.0", "sentencepiece==0.2.0", "tqdm==4.66.5", diff --git a/requirements.txt b/requirements.txt index 27bfce3..4609a33 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,5 +1,5 @@ faiss-cpu==1.8.0 -transformers==4.44.2 +transformers==4.57.1 torch==2.4.0 sentencepiece==0.2.0 tqdm==4.66.5 diff --git a/uv.lock b/uv.lock index 89e82d6..090a162 100644 --- a/uv.lock +++ b/uv.lock @@ -629,7 +629,7 @@ wheels = [ [[package]] name = "semindex" -version = "0.4.0" +version = "0.4.2" source = { editable = "." } dependencies = [ { name = "beautifulsoup4" }, @@ -686,7 +686,7 @@ requires-dist = [ { name = "toml", specifier = ">=0.10.2" }, { name = "torch", specifier = "==2.4.0" }, { name = "tqdm", specifier = "==4.66.5" }, - { name = "transformers", specifier = "==4.44.2" }, + { name = "transformers", specifier = "==4.57.1" }, { name = "tree-sitter", marker = "extra == 'languages'", specifier = ">=0.20" }, { name = "tree-sitter-languages", marker = "extra == 'languages'", specifier = ">=1.10" }, { name = "watchdog", specifier = ">=4.0.0" }, @@ -774,25 +774,27 @@ wheels = [ [[package]] name = "tokenizers" -version = "0.19.1" +version = "0.22.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "huggingface-hub" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/48/04/2071c150f374aab6d5e92aaec38d0f3c368d227dd9e0469a1f0966ac68d1/tokenizers-0.19.1.tar.gz", hash = "sha256:ee59e6680ed0fdbe6b724cf38bd70400a0c1dd623b07ac729087270caeac88e3", size = 321039, upload-time = "2024-04-17T21:40:41.849Z" } +sdist = { url = "https://files.pythonhosted.org/packages/1c/46/fb6854cec3278fbfa4a75b50232c77622bc517ac886156e6afbfa4d8fc6e/tokenizers-0.22.1.tar.gz", hash = "sha256:61de6522785310a309b3407bac22d99c4db5dba349935e99e4d15ea2226af2d9", size = 363123, upload-time = "2025-09-19T09:49:23.424Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/63/90/2890cd096898dcdb596ee172cde40c0f54a9cf43b0736aa260a5501252af/tokenizers-0.19.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:621d670e1b1c281a1c9698ed89451395d318802ff88d1fc1accff0867a06f153", size = 2530580, upload-time = "2024-04-17T21:37:10.688Z" }, - { url = "https://files.pythonhosted.org/packages/74/d1/f4e1e950adb36675dfd8f9d0f4be644f3f3aaf22a5677a4f5c81282b662e/tokenizers-0.19.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d924204a3dbe50b75630bd16f821ebda6a5f729928df30f582fb5aade90c818a", size = 2436682, upload-time = "2024-04-17T21:37:12.966Z" }, - { url = "https://files.pythonhosted.org/packages/ed/30/89b321a16c58d233e301ec15072c0d3ed5014825e72da98604cd3ab2fba1/tokenizers-0.19.1-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:4f3fefdc0446b1a1e6d81cd4c07088ac015665d2e812f6dbba4a06267d1a2c95", size = 3693494, upload-time = "2024-04-17T21:37:14.755Z" }, - { url = "https://files.pythonhosted.org/packages/05/40/fa899f32de483500fbc78befd378fd7afba4270f17db707d1a78c0a4ddc3/tokenizers-0.19.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9620b78e0b2d52ef07b0d428323fb34e8ea1219c5eac98c2596311f20f1f9266", size = 3566541, upload-time = "2024-04-17T21:37:17.067Z" }, - { url = "https://files.pythonhosted.org/packages/67/14/e7da32ae5fb4971830f1ef335932fae3fa57e76b537e852f146c850aefdf/tokenizers-0.19.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:04ce49e82d100594715ac1b2ce87d1a36e61891a91de774755f743babcd0dd52", size = 3430792, upload-time = "2024-04-17T21:37:19.055Z" }, - { url = "https://files.pythonhosted.org/packages/f2/4b/aae61bdb6ab584d2612170801703982ee0e35f8b6adacbeefe5a3b277621/tokenizers-0.19.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c5c2ff13d157afe413bf7e25789879dd463e5a4abfb529a2d8f8473d8042e28f", size = 3962812, upload-time = "2024-04-17T21:37:21.008Z" }, - { url = "https://files.pythonhosted.org/packages/0a/b6/f7b7ef89c4da7b20256e6eab23d3835f05d1ca8f451d31c16cbfe3cd9eb6/tokenizers-0.19.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3174c76efd9d08f836bfccaca7cfec3f4d1c0a4cf3acbc7236ad577cc423c840", size = 4024688, upload-time = "2024-04-17T21:37:23.659Z" }, - { url = "https://files.pythonhosted.org/packages/80/54/12047a69f5b382d7ee72044dc89151a2dd0d13b2c9bdcc22654883704d31/tokenizers-0.19.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7c9d5b6c0e7a1e979bec10ff960fae925e947aab95619a6fdb4c1d8ff3708ce3", size = 3610961, upload-time = "2024-04-17T21:37:26.234Z" }, - { url = "https://files.pythonhosted.org/packages/52/b7/1e8a913d18ac28feeda42d4d2d51781874398fb59cd1c1e2653a4b5742ed/tokenizers-0.19.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:a179856d1caee06577220ebcfa332af046d576fb73454b8f4d4b0ba8324423ea", size = 9631367, upload-time = "2024-04-17T21:37:28.752Z" }, - { url = "https://files.pythonhosted.org/packages/ac/3d/2284f6d99f8f21d09352b88b8cfefa24ab88468d962aeb0aa15c20d76b32/tokenizers-0.19.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:952b80dac1a6492170f8c2429bd11fcaa14377e097d12a1dbe0ef2fb2241e16c", size = 9950121, upload-time = "2024-04-17T21:37:31.741Z" }, - { url = "https://files.pythonhosted.org/packages/2a/94/ec3369dbc9b7200c14c8c7a1a04c78b7a7398d0c001e1b7d1ffe30eb93a0/tokenizers-0.19.1-cp312-none-win32.whl", hash = "sha256:01d62812454c188306755c94755465505836fd616f75067abcae529c35edeb57", size = 2044069, upload-time = "2024-04-17T21:37:35.672Z" }, - { url = "https://files.pythonhosted.org/packages/0c/97/80bff6937e0c67d30c0facacd4f0bcf4254e581aa4995c73cef8c8640e56/tokenizers-0.19.1-cp312-none-win_amd64.whl", hash = "sha256:b70bfbe3a82d3e3fb2a5e9b22a39f8d1740c96c68b6ace0086b39074f08ab89a", size = 2214527, upload-time = "2024-04-17T21:37:39.19Z" }, + { url = "https://files.pythonhosted.org/packages/bf/33/f4b2d94ada7ab297328fc671fed209368ddb82f965ec2224eb1892674c3a/tokenizers-0.22.1-cp39-abi3-macosx_10_12_x86_64.whl", hash = "sha256:59fdb013df17455e5f950b4b834a7b3ee2e0271e6378ccb33aa74d178b513c73", size = 3069318, upload-time = "2025-09-19T09:49:11.848Z" }, + { url = "https://files.pythonhosted.org/packages/1c/58/2aa8c874d02b974990e89ff95826a4852a8b2a273c7d1b4411cdd45a4565/tokenizers-0.22.1-cp39-abi3-macosx_11_0_arm64.whl", hash = "sha256:8d4e484f7b0827021ac5f9f71d4794aaef62b979ab7608593da22b1d2e3c4edc", size = 2926478, upload-time = "2025-09-19T09:49:09.759Z" }, + { url = "https://files.pythonhosted.org/packages/1e/3b/55e64befa1e7bfea963cf4b787b2cea1011362c4193f5477047532ce127e/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:19d2962dd28bc67c1f205ab180578a78eef89ac60ca7ef7cbe9635a46a56422a", size = 3256994, upload-time = "2025-09-19T09:48:56.701Z" }, + { url = "https://files.pythonhosted.org/packages/71/0b/fbfecf42f67d9b7b80fde4aabb2b3110a97fac6585c9470b5bff103a80cb/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:38201f15cdb1f8a6843e6563e6e79f4abd053394992b9bbdf5213ea3469b4ae7", size = 3153141, upload-time = "2025-09-19T09:48:59.749Z" }, + { url = "https://files.pythonhosted.org/packages/17/a9/b38f4e74e0817af8f8ef925507c63c6ae8171e3c4cb2d5d4624bf58fca69/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d1cbe5454c9a15df1b3443c726063d930c16f047a3cc724b9e6e1a91140e5a21", size = 3508049, upload-time = "2025-09-19T09:49:05.868Z" }, + { url = "https://files.pythonhosted.org/packages/d2/48/dd2b3dac46bb9134a88e35d72e1aa4869579eacc1a27238f1577270773ff/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e7d094ae6312d69cc2a872b54b91b309f4f6fbce871ef28eb27b52a98e4d0214", size = 3710730, upload-time = "2025-09-19T09:49:01.832Z" }, + { url = "https://files.pythonhosted.org/packages/93/0e/ccabc8d16ae4ba84a55d41345207c1e2ea88784651a5a487547d80851398/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:afd7594a56656ace95cdd6df4cca2e4059d294c5cfb1679c57824b605556cb2f", size = 3412560, upload-time = "2025-09-19T09:49:03.867Z" }, + { url = "https://files.pythonhosted.org/packages/d0/c6/dc3a0db5a6766416c32c034286d7c2d406da1f498e4de04ab1b8959edd00/tokenizers-0.22.1-cp39-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e2ef6063d7a84994129732b47e7915e8710f27f99f3a3260b8a38fc7ccd083f4", size = 3250221, upload-time = "2025-09-19T09:49:07.664Z" }, + { url = "https://files.pythonhosted.org/packages/d7/a6/2c8486eef79671601ff57b093889a345dd3d576713ef047776015dc66de7/tokenizers-0.22.1-cp39-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:ba0a64f450b9ef412c98f6bcd2a50c6df6e2443b560024a09fa6a03189726879", size = 9345569, upload-time = "2025-09-19T09:49:14.214Z" }, + { url = "https://files.pythonhosted.org/packages/6b/16/32ce667f14c35537f5f605fe9bea3e415ea1b0a646389d2295ec348d5657/tokenizers-0.22.1-cp39-abi3-musllinux_1_2_armv7l.whl", hash = "sha256:331d6d149fa9c7d632cde4490fb8bbb12337fa3a0232e77892be656464f4b446", size = 9271599, upload-time = "2025-09-19T09:49:16.639Z" }, + { url = "https://files.pythonhosted.org/packages/51/7c/a5f7898a3f6baa3fc2685c705e04c98c1094c523051c805cdd9306b8f87e/tokenizers-0.22.1-cp39-abi3-musllinux_1_2_i686.whl", hash = "sha256:607989f2ea68a46cb1dfbaf3e3aabdf3f21d8748312dbeb6263d1b3b66c5010a", size = 9533862, upload-time = "2025-09-19T09:49:19.146Z" }, + { url = "https://files.pythonhosted.org/packages/36/65/7e75caea90bc73c1dd8d40438adf1a7bc26af3b8d0a6705ea190462506e1/tokenizers-0.22.1-cp39-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:a0f307d490295717726598ef6fa4f24af9d484809223bbc253b201c740a06390", size = 9681250, upload-time = "2025-09-19T09:49:21.501Z" }, + { url = "https://files.pythonhosted.org/packages/30/2c/959dddef581b46e6209da82df3b78471e96260e2bc463f89d23b1bf0e52a/tokenizers-0.22.1-cp39-abi3-win32.whl", hash = "sha256:b5120eed1442765cd90b903bb6cfef781fd8fe64e34ccaecbae4c619b7b12a82", size = 2472003, upload-time = "2025-09-19T09:49:27.089Z" }, + { url = "https://files.pythonhosted.org/packages/b3/46/e33a8c93907b631a99377ef4c5f817ab453d0b34f93529421f42ff559671/tokenizers-0.22.1-cp39-abi3-win_amd64.whl", hash = "sha256:65fd6e3fb11ca1e78a6a93602490f134d1fdeb13bcef99389d5102ea318ed138", size = 2674684, upload-time = "2025-09-19T09:49:24.953Z" }, ] [[package]] @@ -850,7 +852,7 @@ wheels = [ [[package]] name = "transformers" -version = "4.44.2" +version = "4.57.1" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "filelock" }, @@ -864,9 +866,9 @@ dependencies = [ { name = "tokenizers" }, { name = "tqdm" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/f8/a3/81de49357a3c6ac4421d48d9662b53293838f217baf3f3bb9eb55f89fab6/transformers-4.44.2.tar.gz", hash = "sha256:36aa17cc92ee154058e426d951684a2dab48751b35b49437896f898931270826", size = 8110312, upload-time = "2024-08-22T16:56:33.522Z" } +sdist = { url = "https://files.pythonhosted.org/packages/d6/68/a39307bcc4116a30b2106f2e689130a48de8bd8a1e635b5e1030e46fcd9e/transformers-4.57.1.tar.gz", hash = "sha256:f06c837959196c75039809636cd964b959f6604b75b8eeec6fdfc0440b89cc55", size = 10142511, upload-time = "2025-10-14T15:39:26.18Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/75/35/07c9879163b603f0e464b0f6e6e628a2340cfc7cdc5ca8e7d52d776710d4/transformers-4.44.2-py3-none-any.whl", hash = "sha256:1c02c65e7bfa5e52a634aff3da52138b583fc6f263c1f28d547dc144ba3d412d", size = 9465369, upload-time = "2024-08-22T16:56:29.207Z" }, + { url = "https://files.pythonhosted.org/packages/71/d3/c16c3b3cf7655a67db1144da94b021c200ac1303f82428f2beef6c2e72bb/transformers-4.57.1-py3-none-any.whl", hash = "sha256:b10d05da8fa67dc41644dbbf9bc45a44cb86ae33da6f9295f5fbf5b7890bd267", size = 11990925, upload-time = "2025-10-14T15:39:23.085Z" }, ] [[package]]