added notebook for positional embeddings

This commit is contained in:
Patryk Bartkowiak 2024-10-26 16:47:44 +00:00
parent 0376f74833
commit 01a1dd82a1
4 changed files with 1320 additions and 1 deletions

3
.gitignore vendored
View File

@ -164,3 +164,6 @@ arxiv-msc-patryk-bartkowiak.pdf
arxiv-msc-patryk-bartkowiak.tar.gz
helpers/*-contribution-declaration.tex
helpers/*-contribution-declaration.pdf
outputs/

View File

@ -5,7 +5,7 @@
groups = ["default"]
strategy = ["inherit_metadata"]
lock_version = "4.5.0"
content_hash = "sha256:bf0a0ea826769cf12a84888d394edd8c3c5599c4d369b8b19b75c2fa5e16f5f0"
content_hash = "sha256:338f5336fd6463c63aa76589adce0319d0bc3a5fb0844ba680636734253fbf02"
[[metadata.targets]]
requires_python = "==3.11.*"
@ -147,6 +147,40 @@ files = [
{file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
]
[[package]]
name = "contourpy"
version = "1.3.0"
requires_python = ">=3.9"
summary = "Python library for calculating contours of 2D quadrilateral grids"
groups = ["default"]
dependencies = [
"numpy>=1.23",
]
files = [
{file = "contourpy-1.3.0-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:0fa4c02abe6c446ba70d96ece336e621efa4aecae43eaa9b030ae5fb92b309ad"},
{file = "contourpy-1.3.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:834e0cfe17ba12f79963861e0f908556b2cedd52e1f75e6578801febcc6a9f49"},
{file = "contourpy-1.3.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dbc4c3217eee163fa3984fd1567632b48d6dfd29216da3ded3d7b844a8014a66"},
{file = "contourpy-1.3.0-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4865cd1d419e0c7a7bf6de1777b185eebdc51470800a9f42b9e9decf17762081"},
{file = "contourpy-1.3.0-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:303c252947ab4b14c08afeb52375b26781ccd6a5ccd81abcdfc1fafd14cf93c1"},
{file = "contourpy-1.3.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:637f674226be46f6ba372fd29d9523dd977a291f66ab2a74fbeb5530bb3f445d"},
{file = "contourpy-1.3.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:76a896b2f195b57db25d6b44e7e03f221d32fe318d03ede41f8b4d9ba1bff53c"},
{file = "contourpy-1.3.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:e1fd23e9d01591bab45546c089ae89d926917a66dceb3abcf01f6105d927e2cb"},
{file = "contourpy-1.3.0-cp311-cp311-win32.whl", hash = "sha256:d402880b84df3bec6eab53cd0cf802cae6a2ef9537e70cf75e91618a3801c20c"},
{file = "contourpy-1.3.0-cp311-cp311-win_amd64.whl", hash = "sha256:6cb6cc968059db9c62cb35fbf70248f40994dfcd7aa10444bbf8b3faeb7c2d67"},
{file = "contourpy-1.3.0.tar.gz", hash = "sha256:7ffa0db17717a8ffb127efd0c95a4362d996b892c2904db72428d5b52e1938a4"},
]
[[package]]
name = "cycler"
version = "0.12.1"
requires_python = ">=3.8"
summary = "Composable style cycles"
groups = ["default"]
files = [
{file = "cycler-0.12.1-py3-none-any.whl", hash = "sha256:85cef7cff222d8644161529808465972e51340599459b8ac3ccbac5a854e0d30"},
{file = "cycler-0.12.1.tar.gz", hash = "sha256:88bb128f02ba341da8ef447245a9e138fae777f6a23943da4540077d3601eb1c"},
]
[[package]]
name = "datasets"
version = "3.0.1"
@ -209,6 +243,25 @@ files = [
{file = "filelock-3.16.1.tar.gz", hash = "sha256:c249fbfcd5db47e5e2d6d62198e565475ee65e4831e2561c8e313fa7eb961435"},
]
[[package]]
name = "fonttools"
version = "4.54.1"
requires_python = ">=3.8"
summary = "Tools to manipulate font files"
groups = ["default"]
files = [
{file = "fonttools-4.54.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:5419771b64248484299fa77689d4f3aeed643ea6630b2ea750eeab219588ba20"},
{file = "fonttools-4.54.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:301540e89cf4ce89d462eb23a89464fef50915255ece765d10eee8b2bf9d75b2"},
{file = "fonttools-4.54.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:76ae5091547e74e7efecc3cbf8e75200bc92daaeb88e5433c5e3e95ea8ce5aa7"},
{file = "fonttools-4.54.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:82834962b3d7c5ca98cb56001c33cf20eb110ecf442725dc5fdf36d16ed1ab07"},
{file = "fonttools-4.54.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:d26732ae002cc3d2ecab04897bb02ae3f11f06dd7575d1df46acd2f7c012a8d8"},
{file = "fonttools-4.54.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:58974b4987b2a71ee08ade1e7f47f410c367cdfc5a94fabd599c88165f56213a"},
{file = "fonttools-4.54.1-cp311-cp311-win32.whl", hash = "sha256:ab774fa225238986218a463f3fe151e04d8c25d7de09df7f0f5fce27b1243dbc"},
{file = "fonttools-4.54.1-cp311-cp311-win_amd64.whl", hash = "sha256:07e005dc454eee1cc60105d6a29593459a06321c21897f769a281ff2d08939f6"},
{file = "fonttools-4.54.1-py3-none-any.whl", hash = "sha256:37cddd62d83dc4f72f7c3f3c2bcf2697e89a30efb152079896544a93907733bd"},
{file = "fonttools-4.54.1.tar.gz", hash = "sha256:957f669d4922f92c171ba01bef7f29410668db09f6c02111e22b2bce446f3285"},
]
[[package]]
name = "frozenlist"
version = "1.4.1"
@ -336,6 +389,43 @@ files = [
{file = "jinja2-3.1.4.tar.gz", hash = "sha256:4a3aee7acbbe7303aede8e9648d13b8bf88a429282aa6122a993f0ac800cb369"},
]
[[package]]
name = "joblib"
version = "1.4.2"
requires_python = ">=3.8"
summary = "Lightweight pipelining with Python functions"
groups = ["default"]
files = [
{file = "joblib-1.4.2-py3-none-any.whl", hash = "sha256:06d478d5674cbc267e7496a410ee875abd68e4340feff4490bcb7afb88060ae6"},
{file = "joblib-1.4.2.tar.gz", hash = "sha256:2382c5816b2636fbd20a09e0f4e9dad4736765fdfb7dca582943b9c1366b3f0e"},
]
[[package]]
name = "kiwisolver"
version = "1.4.7"
requires_python = ">=3.8"
summary = "A fast implementation of the Cassowary constraint solver"
groups = ["default"]
files = [
{file = "kiwisolver-1.4.7-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:d2b0e12a42fb4e72d509fc994713d099cbb15ebf1103545e8a45f14da2dfca54"},
{file = "kiwisolver-1.4.7-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:2a8781ac3edc42ea4b90bc23e7d37b665d89423818e26eb6df90698aa2287c95"},
{file = "kiwisolver-1.4.7-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:46707a10836894b559e04b0fd143e343945c97fd170d69a2d26d640b4e297935"},
{file = "kiwisolver-1.4.7-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ef97b8df011141c9b0f6caf23b29379f87dd13183c978a30a3c546d2c47314cb"},
{file = "kiwisolver-1.4.7-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3ab58c12a2cd0fc769089e6d38466c46d7f76aced0a1f54c77652446733d2d02"},
{file = "kiwisolver-1.4.7-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:803b8e1459341c1bb56d1c5c010406d5edec8a0713a0945851290a7930679b51"},
{file = "kiwisolver-1.4.7-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f9a9e8a507420fe35992ee9ecb302dab68550dedc0da9e2880dd88071c5fb052"},
{file = "kiwisolver-1.4.7-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:18077b53dc3bb490e330669a99920c5e6a496889ae8c63b58fbc57c3d7f33a18"},
{file = "kiwisolver-1.4.7-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:6af936f79086a89b3680a280c47ea90b4df7047b5bdf3aa5c524bbedddb9e545"},
{file = "kiwisolver-1.4.7-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:3abc5b19d24af4b77d1598a585b8a719beb8569a71568b66f4ebe1fb0449460b"},
{file = "kiwisolver-1.4.7-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:933d4de052939d90afbe6e9d5273ae05fb836cc86c15b686edd4b3560cc0ee36"},
{file = "kiwisolver-1.4.7-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:65e720d2ab2b53f1f72fb5da5fb477455905ce2c88aaa671ff0a447c2c80e8e3"},
{file = "kiwisolver-1.4.7-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:3bf1ed55088f214ba6427484c59553123fdd9b218a42bbc8c6496d6754b1e523"},
{file = "kiwisolver-1.4.7-cp311-cp311-win32.whl", hash = "sha256:4c00336b9dd5ad96d0a558fd18a8b6f711b7449acce4c157e7343ba92dd0cf3d"},
{file = "kiwisolver-1.4.7-cp311-cp311-win_amd64.whl", hash = "sha256:929e294c1ac1e9f615c62a4e4313ca1823ba37326c164ec720a803287c4c499b"},
{file = "kiwisolver-1.4.7-cp311-cp311-win_arm64.whl", hash = "sha256:e33e8fbd440c917106b237ef1a2f1449dfbb9b6f6e1ce17c94cd6a1e0d438376"},
{file = "kiwisolver-1.4.7.tar.gz", hash = "sha256:9893ff81bd7107f7b685d3017cc6583daadb4fc26e4a888350df530e41980a60"},
]
[[package]]
name = "markupsafe"
version = "3.0.2"
@ -356,6 +446,34 @@ files = [
{file = "markupsafe-3.0.2.tar.gz", hash = "sha256:ee55d3edf80167e48ea11a923c7386f4669df67d7994554387f84e7d8b0a2bf0"},
]
[[package]]
name = "matplotlib"
version = "3.9.2"
requires_python = ">=3.9"
summary = "Python plotting package"
groups = ["default"]
dependencies = [
"contourpy>=1.0.1",
"cycler>=0.10",
"fonttools>=4.22.0",
"importlib-resources>=3.2.0; python_version < \"3.10\"",
"kiwisolver>=1.3.1",
"numpy>=1.23",
"packaging>=20.0",
"pillow>=8",
"pyparsing>=2.3.1",
"python-dateutil>=2.7",
]
files = [
{file = "matplotlib-3.9.2-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:d8dd059447824eec055e829258ab092b56bb0579fc3164fa09c64f3acd478772"},
{file = "matplotlib-3.9.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:c797dac8bb9c7a3fd3382b16fe8f215b4cf0f22adccea36f1545a6d7be310b41"},
{file = "matplotlib-3.9.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d719465db13267bcef19ea8954a971db03b9f48b4647e3860e4bc8e6ed86610f"},
{file = "matplotlib-3.9.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8912ef7c2362f7193b5819d17dae8629b34a95c58603d781329712ada83f9447"},
{file = "matplotlib-3.9.2-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:7741f26a58a240f43bee74965c4882b6c93df3e7eb3de160126d8c8f53a6ae6e"},
{file = "matplotlib-3.9.2-cp311-cp311-win_amd64.whl", hash = "sha256:ae82a14dab96fbfad7965403c643cafe6515e386de723e498cf3eeb1e0b70cc7"},
{file = "matplotlib-3.9.2.tar.gz", hash = "sha256:96ab43906269ca64a6366934106fa01534454a69e471b7bf3d79083981aaab92"},
]
[[package]]
name = "mpmath"
version = "1.3.0"
@ -644,6 +762,27 @@ files = [
{file = "pandas-2.2.3.tar.gz", hash = "sha256:4f18ba62b61d7e192368b84517265a99b4d7ee8912f8708660fb4a366cc82667"},
]
[[package]]
name = "pillow"
version = "11.0.0"
requires_python = ">=3.9"
summary = "Python Imaging Library (Fork)"
groups = ["default"]
files = [
{file = "pillow-11.0.0-cp311-cp311-macosx_10_10_x86_64.whl", hash = "sha256:1c1d72714f429a521d8d2d018badc42414c3077eb187a59579f28e4270b4b0fc"},
{file = "pillow-11.0.0-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:499c3a1b0d6fc8213519e193796eb1a86a1be4b1877d678b30f83fd979811d1a"},
{file = "pillow-11.0.0-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c8b2351c85d855293a299038e1f89db92a2f35e8d2f783489c6f0b2b5f3fe8a3"},
{file = "pillow-11.0.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6f4dba50cfa56f910241eb7f883c20f1e7b1d8f7d91c750cd0b318bad443f4d5"},
{file = "pillow-11.0.0-cp311-cp311-manylinux_2_28_aarch64.whl", hash = "sha256:5ddbfd761ee00c12ee1be86c9c0683ecf5bb14c9772ddbd782085779a63dd55b"},
{file = "pillow-11.0.0-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:45c566eb10b8967d71bf1ab8e4a525e5a93519e29ea071459ce517f6b903d7fa"},
{file = "pillow-11.0.0-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:b4fd7bd29610a83a8c9b564d457cf5bd92b4e11e79a4ee4716a63c959699b306"},
{file = "pillow-11.0.0-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:cb929ca942d0ec4fac404cbf520ee6cac37bf35be479b970c4ffadf2b6a1cad9"},
{file = "pillow-11.0.0-cp311-cp311-win32.whl", hash = "sha256:006bcdd307cc47ba43e924099a038cbf9591062e6c50e570819743f5607404f5"},
{file = "pillow-11.0.0-cp311-cp311-win_amd64.whl", hash = "sha256:52a2d8323a465f84faaba5236567d212c3668f2ab53e1c74c15583cf507a0291"},
{file = "pillow-11.0.0-cp311-cp311-win_arm64.whl", hash = "sha256:16095692a253047fe3ec028e951fa4221a1f3ed3d80c397e83541a3037ff67c9"},
{file = "pillow-11.0.0.tar.gz", hash = "sha256:72bacbaf24ac003fea9bff9837d1eedb6088758d41e100c1552930151f677739"},
]
[[package]]
name = "platformdirs"
version = "4.3.6"
@ -736,6 +875,17 @@ files = [
{file = "pyarrow-17.0.0.tar.gz", hash = "sha256:4beca9521ed2c0921c1023e68d097d0299b62c362639ea315572a58f3f50fd28"},
]
[[package]]
name = "pyparsing"
version = "3.2.0"
requires_python = ">=3.9"
summary = "pyparsing module - Classes and methods to define and execute parsing grammars"
groups = ["default"]
files = [
{file = "pyparsing-3.2.0-py3-none-any.whl", hash = "sha256:93d9577b88da0bbea8cc8334ee8b918ed014968fd2ec383e868fb8afb1ccef84"},
{file = "pyparsing-3.2.0.tar.gz", hash = "sha256:cbf74e27246d595d9a74b186b810f6fbb86726dbf3b9532efb343f6d7294fe9c"},
]
[[package]]
name = "python-dateutil"
version = "2.9.0.post0"
@ -843,6 +993,64 @@ files = [
{file = "safetensors-0.4.5.tar.gz", hash = "sha256:d73de19682deabb02524b3d5d1f8b3aaba94c72f1bbfc7911b9b9d5d391c0310"},
]
[[package]]
name = "scikit-learn"
version = "1.5.2"
requires_python = ">=3.9"
summary = "A set of python modules for machine learning and data mining"
groups = ["default"]
dependencies = [
"joblib>=1.2.0",
"numpy>=1.19.5",
"scipy>=1.6.0",
"threadpoolctl>=3.1.0",
]
files = [
{file = "scikit_learn-1.5.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:03b6158efa3faaf1feea3faa884c840ebd61b6484167c711548fce208ea09445"},
{file = "scikit_learn-1.5.2-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:1ff45e26928d3b4eb767a8f14a9a6efbf1cbff7c05d1fb0f95f211a89fd4f5de"},
{file = "scikit_learn-1.5.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f763897fe92d0e903aa4847b0aec0e68cadfff77e8a0687cabd946c89d17e675"},
{file = "scikit_learn-1.5.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f8b0ccd4a902836493e026c03256e8b206656f91fbcc4fde28c57a5b752561f1"},
{file = "scikit_learn-1.5.2-cp311-cp311-win_amd64.whl", hash = "sha256:6c16d84a0d45e4894832b3c4d0bf73050939e21b99b01b6fd59cbb0cf39163b6"},
{file = "scikit_learn-1.5.2.tar.gz", hash = "sha256:b4237ed7b3fdd0a4882792e68ef2545d5baa50aca3bb45aa7df468138ad8f94d"},
]
[[package]]
name = "scipy"
version = "1.14.1"
requires_python = ">=3.10"
summary = "Fundamental algorithms for scientific computing in Python"
groups = ["default"]
dependencies = [
"numpy<2.3,>=1.23.5",
]
files = [
{file = "scipy-1.14.1-cp311-cp311-macosx_10_13_x86_64.whl", hash = "sha256:2da0469a4ef0ecd3693761acbdc20f2fdeafb69e6819cc081308cc978153c675"},
{file = "scipy-1.14.1-cp311-cp311-macosx_12_0_arm64.whl", hash = "sha256:c0ee987efa6737242745f347835da2cc5bb9f1b42996a4d97d5c7ff7928cb6f2"},
{file = "scipy-1.14.1-cp311-cp311-macosx_14_0_arm64.whl", hash = "sha256:3a1b111fac6baec1c1d92f27e76511c9e7218f1695d61b59e05e0fe04dc59617"},
{file = "scipy-1.14.1-cp311-cp311-macosx_14_0_x86_64.whl", hash = "sha256:8475230e55549ab3f207bff11ebfc91c805dc3463ef62eda3ccf593254524ce8"},
{file = "scipy-1.14.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:278266012eb69f4a720827bdd2dc54b2271c97d84255b2faaa8f161a158c3b37"},
{file = "scipy-1.14.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fef8c87f8abfb884dac04e97824b61299880c43f4ce675dd2cbeadd3c9b466d2"},
{file = "scipy-1.14.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:b05d43735bb2f07d689f56f7b474788a13ed8adc484a85aa65c0fd931cf9ccd2"},
{file = "scipy-1.14.1-cp311-cp311-win_amd64.whl", hash = "sha256:716e389b694c4bb564b4fc0c51bc84d381735e0d39d3f26ec1af2556ec6aad94"},
{file = "scipy-1.14.1.tar.gz", hash = "sha256:5a275584e726026a5699459aa72f828a610821006228e841b94275c4a7c08417"},
]
[[package]]
name = "seaborn"
version = "0.13.2"
requires_python = ">=3.8"
summary = "Statistical data visualization"
groups = ["default"]
dependencies = [
"matplotlib!=3.6.1,>=3.4",
"numpy!=1.24.0,>=1.20",
"pandas>=1.2",
]
files = [
{file = "seaborn-0.13.2-py3-none-any.whl", hash = "sha256:636f8336facf092165e27924f223d3c62ca560b1f2bb5dff7ab7fad265361987"},
{file = "seaborn-0.13.2.tar.gz", hash = "sha256:93e60a40988f4d65e9f4885df477e2fdaff6b73a9ded434c1ab356dd57eefff7"},
]
[[package]]
name = "sentry-sdk"
version = "2.17.0"
@ -928,6 +1136,17 @@ files = [
{file = "sympy-1.13.1.tar.gz", hash = "sha256:9cebf7e04ff162015ce31c9c6c9144daa34a93bd082f54fd8f12deca4f47515f"},
]
[[package]]
name = "threadpoolctl"
version = "3.5.0"
requires_python = ">=3.8"
summary = "threadpoolctl"
groups = ["default"]
files = [
{file = "threadpoolctl-3.5.0-py3-none-any.whl", hash = "sha256:56c1e26c150397e58c4926da8eeee87533b1e32bef131bd4bf6a2f45f3185467"},
{file = "threadpoolctl-3.5.0.tar.gz", hash = "sha256:082433502dd922bf738de0d8bcc4fdcbf0979ff44c42bd40f5af8a282f6fa107"},
]
[[package]]
name = "tokenizers"
version = "0.20.1"

View File

@ -13,6 +13,9 @@ dependencies = [
"transformers==4.45.2",
"datasets==3.0.1",
"huggingface-hub==0.26.0",
"matplotlib==3.9.2",
"scikit-learn==1.5.2",
"seaborn==0.13.2",
]
requires-python = "==3.11.*"
readme = "README.md"

File diff suppressed because one or more lines are too long