From f938825272d0f0b17a14a315f7f38540db725557 Mon Sep 17 00:00:00 2001 From: OlivierDehaene <23298448+OlivierDehaene@users.noreply.github.com> Date: Thu, 28 Sep 2023 09:16:03 +0200 Subject: [PATCH] fix tests --- clients/python/README.md | 8 + clients/python/poetry.lock | 201 ++++++++++++++++++------ clients/python/pyproject.toml | 2 +- clients/python/text_generation/types.py | 8 +- docs/source/basic_tutorials/launcher.md | 71 +++++++-- 5 files changed, 222 insertions(+), 68 deletions(-) diff --git a/clients/python/README.md b/clients/python/README.md index 4e0e564c..82f3ee0c 100644 --- a/clients/python/README.md +++ b/clients/python/README.md @@ -140,6 +140,8 @@ class Parameters: watermark: bool # Get decoder input token logprobs and ids decoder_input_details: bool + # Return the N most likely tokens at each step + top_n_tokens: Optional[int] # Decoder input tokens class InputToken: @@ -189,6 +191,8 @@ class BestOfSequence: prefill: List[InputToken] # Generated tokens tokens: List[Token] + # Most likely tokens + top_tokens: Optional[List[List[Token]]] # `generate` details @@ -203,6 +207,8 @@ class Details: prefill: List[InputToken] # Generated tokens tokens: List[Token] + # Most likely tokens + top_tokens: Optional[List[List[Token]]] # Additional sequences when using the `best_of` parameter best_of_sequences: Optional[List[BestOfSequence]] @@ -229,6 +235,8 @@ class StreamDetails: class StreamResponse: # Generated token token: Token + # Most likely tokens + top_tokens: Optional[List[Token]] # Complete generated text # Only available when the generation is finished generated_text: Optional[str] diff --git a/clients/python/poetry.lock b/clients/python/poetry.lock index e038ad9b..2d4e45d2 100644 --- a/clients/python/poetry.lock +++ b/clients/python/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 1.5.1 and should not be changed by hand. +# This file is automatically @generated by Poetry 1.6.1 and should not be changed by hand. [[package]] name = "aiohttp" @@ -124,6 +124,20 @@ files = [ [package.dependencies] frozenlist = ">=1.1.0" +[[package]] +name = "annotated-types" +version = "0.5.0" +description = "Reusable constraint types to use with typing.Annotated" +optional = false +python-versions = ">=3.7" +files = [ + {file = "annotated_types-0.5.0-py3-none-any.whl", hash = "sha256:58da39888f92c276ad970249761ebea80ba544b77acddaa1a4d6cf78287d45fd"}, + {file = "annotated_types-0.5.0.tar.gz", hash = "sha256:47cdc3490d9ac1506ce92c7aaa76c579dc3509ff11e098fc867e5130ab7be802"}, +] + +[package.dependencies] +typing-extensions = {version = ">=4.0.0", markers = "python_version < \"3.9\""} + [[package]] name = "async-timeout" version = "4.0.3" @@ -693,55 +707,140 @@ files = [ [[package]] name = "pydantic" -version = "1.10.12" -description = "Data validation and settings management using python type hints" +version = "2.4.2" +description = "Data validation using Python type hints" optional = false python-versions = ">=3.7" files = [ - {file = "pydantic-1.10.12-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:a1fcb59f2f355ec350073af41d927bf83a63b50e640f4dbaa01053a28b7a7718"}, - {file = "pydantic-1.10.12-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:b7ccf02d7eb340b216ec33e53a3a629856afe1c6e0ef91d84a4e6f2fb2ca70fe"}, - {file = "pydantic-1.10.12-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8fb2aa3ab3728d950bcc885a2e9eff6c8fc40bc0b7bb434e555c215491bcf48b"}, - {file = "pydantic-1.10.12-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:771735dc43cf8383959dc9b90aa281f0b6092321ca98677c5fb6125a6f56d58d"}, - {file = "pydantic-1.10.12-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:ca48477862372ac3770969b9d75f1bf66131d386dba79506c46d75e6b48c1e09"}, - {file = "pydantic-1.10.12-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a5e7add47a5b5a40c49b3036d464e3c7802f8ae0d1e66035ea16aa5b7a3923ed"}, - {file = "pydantic-1.10.12-cp310-cp310-win_amd64.whl", hash = "sha256:e4129b528c6baa99a429f97ce733fff478ec955513630e61b49804b6cf9b224a"}, - {file = "pydantic-1.10.12-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:b0d191db0f92dfcb1dec210ca244fdae5cbe918c6050b342d619c09d31eea0cc"}, - {file = "pydantic-1.10.12-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:795e34e6cc065f8f498c89b894a3c6da294a936ee71e644e4bd44de048af1405"}, - {file = "pydantic-1.10.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:69328e15cfda2c392da4e713443c7dbffa1505bc9d566e71e55abe14c97ddc62"}, - {file = "pydantic-1.10.12-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2031de0967c279df0d8a1c72b4ffc411ecd06bac607a212892757db7462fc494"}, - {file = "pydantic-1.10.12-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:ba5b2e6fe6ca2b7e013398bc7d7b170e21cce322d266ffcd57cca313e54fb246"}, - {file = "pydantic-1.10.12-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:2a7bac939fa326db1ab741c9d7f44c565a1d1e80908b3797f7f81a4f86bc8d33"}, - {file = "pydantic-1.10.12-cp311-cp311-win_amd64.whl", hash = "sha256:87afda5539d5140cb8ba9e8b8c8865cb5b1463924d38490d73d3ccfd80896b3f"}, - {file = "pydantic-1.10.12-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:549a8e3d81df0a85226963611950b12d2d334f214436a19537b2efed61b7639a"}, - {file = "pydantic-1.10.12-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:598da88dfa127b666852bef6d0d796573a8cf5009ffd62104094a4fe39599565"}, - {file = "pydantic-1.10.12-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ba5c4a8552bff16c61882db58544116d021d0b31ee7c66958d14cf386a5b5350"}, - {file = "pydantic-1.10.12-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:c79e6a11a07da7374f46970410b41d5e266f7f38f6a17a9c4823db80dadf4303"}, - {file = "pydantic-1.10.12-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:ab26038b8375581dc832a63c948f261ae0aa21f1d34c1293469f135fa92972a5"}, - {file = "pydantic-1.10.12-cp37-cp37m-win_amd64.whl", hash = "sha256:e0a16d274b588767602b7646fa05af2782576a6cf1022f4ba74cbb4db66f6ca8"}, - {file = "pydantic-1.10.12-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:6a9dfa722316f4acf4460afdf5d41d5246a80e249c7ff475c43a3a1e9d75cf62"}, - {file = "pydantic-1.10.12-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:a73f489aebd0c2121ed974054cb2759af8a9f747de120acd2c3394cf84176ccb"}, - {file = "pydantic-1.10.12-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6b30bcb8cbfccfcf02acb8f1a261143fab622831d9c0989707e0e659f77a18e0"}, - {file = "pydantic-1.10.12-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2fcfb5296d7877af406ba1547dfde9943b1256d8928732267e2653c26938cd9c"}, - {file = "pydantic-1.10.12-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:2f9a6fab5f82ada41d56b0602606a5506aab165ca54e52bc4545028382ef1c5d"}, - {file = "pydantic-1.10.12-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:dea7adcc33d5d105896401a1f37d56b47d443a2b2605ff8a969a0ed5543f7e33"}, - {file = "pydantic-1.10.12-cp38-cp38-win_amd64.whl", hash = "sha256:1eb2085c13bce1612da8537b2d90f549c8cbb05c67e8f22854e201bde5d98a47"}, - {file = "pydantic-1.10.12-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:ef6c96b2baa2100ec91a4b428f80d8f28a3c9e53568219b6c298c1125572ebc6"}, - {file = "pydantic-1.10.12-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:6c076be61cd0177a8433c0adcb03475baf4ee91edf5a4e550161ad57fc90f523"}, - {file = "pydantic-1.10.12-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2d5a58feb9a39f481eda4d5ca220aa8b9d4f21a41274760b9bc66bfd72595b86"}, - {file = "pydantic-1.10.12-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e5f805d2d5d0a41633651a73fa4ecdd0b3d7a49de4ec3fadf062fe16501ddbf1"}, - {file = "pydantic-1.10.12-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:1289c180abd4bd4555bb927c42ee42abc3aee02b0fb2d1223fb7c6e5bef87dbe"}, - {file = "pydantic-1.10.12-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:5d1197e462e0364906cbc19681605cb7c036f2475c899b6f296104ad42b9f5fb"}, - {file = "pydantic-1.10.12-cp39-cp39-win_amd64.whl", hash = "sha256:fdbdd1d630195689f325c9ef1a12900524dceb503b00a987663ff4f58669b93d"}, - {file = "pydantic-1.10.12-py3-none-any.whl", hash = "sha256:b749a43aa51e32839c9d71dc67eb1e4221bb04af1033a32e3923d46f9effa942"}, - {file = "pydantic-1.10.12.tar.gz", hash = "sha256:0fe8a415cea8f340e7a9af9c54fc71a649b43e8ca3cc732986116b3cb135d303"}, + {file = "pydantic-2.4.2-py3-none-any.whl", hash = "sha256:bc3ddf669d234f4220e6e1c4d96b061abe0998185a8d7855c0126782b7abc8c1"}, + {file = "pydantic-2.4.2.tar.gz", hash = "sha256:94f336138093a5d7f426aac732dcfe7ab4eb4da243c88f891d65deb4a2556ee7"}, ] [package.dependencies] -typing-extensions = ">=4.2.0" +annotated-types = ">=0.4.0" +pydantic-core = "2.10.1" +typing-extensions = ">=4.6.1" [package.extras] -dotenv = ["python-dotenv (>=0.10.4)"] -email = ["email-validator (>=1.0.3)"] +email = ["email-validator (>=2.0.0)"] + +[[package]] +name = "pydantic-core" +version = "2.10.1" +description = "" +optional = false +python-versions = ">=3.7" +files = [ + {file = "pydantic_core-2.10.1-cp310-cp310-macosx_10_7_x86_64.whl", hash = "sha256:d64728ee14e667ba27c66314b7d880b8eeb050e58ffc5fec3b7a109f8cddbd63"}, + {file = "pydantic_core-2.10.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:48525933fea744a3e7464c19bfede85df4aba79ce90c60b94d8b6e1eddd67096"}, + {file = "pydantic_core-2.10.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ef337945bbd76cce390d1b2496ccf9f90b1c1242a3a7bc242ca4a9fc5993427a"}, + {file = "pydantic_core-2.10.1-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:a1392e0638af203cee360495fd2cfdd6054711f2db5175b6e9c3c461b76f5175"}, + {file = "pydantic_core-2.10.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:0675ba5d22de54d07bccde38997e780044dcfa9a71aac9fd7d4d7a1d2e3e65f7"}, + {file = "pydantic_core-2.10.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:128552af70a64660f21cb0eb4876cbdadf1a1f9d5de820fed6421fa8de07c893"}, + {file = "pydantic_core-2.10.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f6e6aed5818c264412ac0598b581a002a9f050cb2637a84979859e70197aa9e"}, + {file = "pydantic_core-2.10.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:ecaac27da855b8d73f92123e5f03612b04c5632fd0a476e469dfc47cd37d6b2e"}, + {file = "pydantic_core-2.10.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:b3c01c2fb081fced3bbb3da78510693dc7121bb893a1f0f5f4b48013201f362e"}, + {file = "pydantic_core-2.10.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:92f675fefa977625105708492850bcbc1182bfc3e997f8eecb866d1927c98ae6"}, + {file = "pydantic_core-2.10.1-cp310-none-win32.whl", hash = "sha256:420a692b547736a8d8703c39ea935ab5d8f0d2573f8f123b0a294e49a73f214b"}, + {file = "pydantic_core-2.10.1-cp310-none-win_amd64.whl", hash = "sha256:0880e239827b4b5b3e2ce05e6b766a7414e5f5aedc4523be6b68cfbc7f61c5d0"}, + {file = "pydantic_core-2.10.1-cp311-cp311-macosx_10_7_x86_64.whl", hash = "sha256:073d4a470b195d2b2245d0343569aac7e979d3a0dcce6c7d2af6d8a920ad0bea"}, + {file = "pydantic_core-2.10.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:600d04a7b342363058b9190d4e929a8e2e715c5682a70cc37d5ded1e0dd370b4"}, + {file = "pydantic_core-2.10.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:39215d809470f4c8d1881758575b2abfb80174a9e8daf8f33b1d4379357e417c"}, + {file = "pydantic_core-2.10.1-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:eeb3d3d6b399ffe55f9a04e09e635554012f1980696d6b0aca3e6cf42a17a03b"}, + {file = "pydantic_core-2.10.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a7a7902bf75779bc12ccfc508bfb7a4c47063f748ea3de87135d433a4cca7a2f"}, + {file = "pydantic_core-2.10.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3625578b6010c65964d177626fde80cf60d7f2e297d56b925cb5cdeda6e9925a"}, + {file = "pydantic_core-2.10.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:caa48fc31fc7243e50188197b5f0c4228956f97b954f76da157aae7f67269ae8"}, + {file = "pydantic_core-2.10.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:07ec6d7d929ae9c68f716195ce15e745b3e8fa122fc67698ac6498d802ed0fa4"}, + {file = "pydantic_core-2.10.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e6f31a17acede6a8cd1ae2d123ce04d8cca74056c9d456075f4f6f85de055607"}, + {file = "pydantic_core-2.10.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:d8f1ebca515a03e5654f88411420fea6380fc841d1bea08effb28184e3d4899f"}, + {file = "pydantic_core-2.10.1-cp311-none-win32.whl", hash = "sha256:6db2eb9654a85ada248afa5a6db5ff1cf0f7b16043a6b070adc4a5be68c716d6"}, + {file = "pydantic_core-2.10.1-cp311-none-win_amd64.whl", hash = "sha256:4a5be350f922430997f240d25f8219f93b0c81e15f7b30b868b2fddfc2d05f27"}, + {file = "pydantic_core-2.10.1-cp311-none-win_arm64.whl", hash = "sha256:5fdb39f67c779b183b0c853cd6b45f7db84b84e0571b3ef1c89cdb1dfc367325"}, + {file = "pydantic_core-2.10.1-cp312-cp312-macosx_10_7_x86_64.whl", hash = "sha256:b1f22a9ab44de5f082216270552aa54259db20189e68fc12484873d926426921"}, + {file = "pydantic_core-2.10.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8572cadbf4cfa95fb4187775b5ade2eaa93511f07947b38f4cd67cf10783b118"}, + {file = "pydantic_core-2.10.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:db9a28c063c7c00844ae42a80203eb6d2d6bbb97070cfa00194dff40e6f545ab"}, + {file = "pydantic_core-2.10.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:0e2a35baa428181cb2270a15864ec6286822d3576f2ed0f4cd7f0c1708472aff"}, + {file = "pydantic_core-2.10.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:05560ab976012bf40f25d5225a58bfa649bb897b87192a36c6fef1ab132540d7"}, + {file = "pydantic_core-2.10.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d6495008733c7521a89422d7a68efa0a0122c99a5861f06020ef5b1f51f9ba7c"}, + {file = "pydantic_core-2.10.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:14ac492c686defc8e6133e3a2d9eaf5261b3df26b8ae97450c1647286750b901"}, + {file = "pydantic_core-2.10.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:8282bab177a9a3081fd3d0a0175a07a1e2bfb7fcbbd949519ea0980f8a07144d"}, + {file = "pydantic_core-2.10.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:aafdb89fdeb5fe165043896817eccd6434aee124d5ee9b354f92cd574ba5e78f"}, + {file = "pydantic_core-2.10.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:f6defd966ca3b187ec6c366604e9296f585021d922e666b99c47e78738b5666c"}, + {file = "pydantic_core-2.10.1-cp312-none-win32.whl", hash = "sha256:7c4d1894fe112b0864c1fa75dffa045720a194b227bed12f4be7f6045b25209f"}, + {file = "pydantic_core-2.10.1-cp312-none-win_amd64.whl", hash = "sha256:5994985da903d0b8a08e4935c46ed8daf5be1cf217489e673910951dc533d430"}, + {file = "pydantic_core-2.10.1-cp312-none-win_arm64.whl", hash = "sha256:0d8a8adef23d86d8eceed3e32e9cca8879c7481c183f84ed1a8edc7df073af94"}, + {file = "pydantic_core-2.10.1-cp37-cp37m-macosx_10_7_x86_64.whl", hash = "sha256:9badf8d45171d92387410b04639d73811b785b5161ecadabf056ea14d62d4ede"}, + {file = "pydantic_core-2.10.1-cp37-cp37m-macosx_11_0_arm64.whl", hash = "sha256:ebedb45b9feb7258fac0a268a3f6bec0a2ea4d9558f3d6f813f02ff3a6dc6698"}, + {file = "pydantic_core-2.10.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:cfe1090245c078720d250d19cb05d67e21a9cd7c257698ef139bc41cf6c27b4f"}, + {file = "pydantic_core-2.10.1-cp37-cp37m-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e357571bb0efd65fd55f18db0a2fb0ed89d0bb1d41d906b138f088933ae618bb"}, + {file = "pydantic_core-2.10.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b3dcd587b69bbf54fc04ca157c2323b8911033e827fffaecf0cafa5a892a0904"}, + {file = "pydantic_core-2.10.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9c120c9ce3b163b985a3b966bb701114beb1da4b0468b9b236fc754783d85aa3"}, + {file = "pydantic_core-2.10.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:15d6bca84ffc966cc9976b09a18cf9543ed4d4ecbd97e7086f9ce9327ea48891"}, + {file = "pydantic_core-2.10.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5cabb9710f09d5d2e9e2748c3e3e20d991a4c5f96ed8f1132518f54ab2967221"}, + {file = "pydantic_core-2.10.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:82f55187a5bebae7d81d35b1e9aaea5e169d44819789837cdd4720d768c55d15"}, + {file = "pydantic_core-2.10.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:1d40f55222b233e98e3921df7811c27567f0e1a4411b93d4c5c0f4ce131bc42f"}, + {file = "pydantic_core-2.10.1-cp37-none-win32.whl", hash = "sha256:14e09ff0b8fe6e46b93d36a878f6e4a3a98ba5303c76bb8e716f4878a3bee92c"}, + {file = "pydantic_core-2.10.1-cp37-none-win_amd64.whl", hash = "sha256:1396e81b83516b9d5c9e26a924fa69164156c148c717131f54f586485ac3c15e"}, + {file = "pydantic_core-2.10.1-cp38-cp38-macosx_10_7_x86_64.whl", hash = "sha256:6835451b57c1b467b95ffb03a38bb75b52fb4dc2762bb1d9dbed8de31ea7d0fc"}, + {file = "pydantic_core-2.10.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:b00bc4619f60c853556b35f83731bd817f989cba3e97dc792bb8c97941b8053a"}, + {file = "pydantic_core-2.10.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0fa467fd300a6f046bdb248d40cd015b21b7576c168a6bb20aa22e595c8ffcdd"}, + {file = "pydantic_core-2.10.1-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d99277877daf2efe074eae6338453a4ed54a2d93fb4678ddfe1209a0c93a2468"}, + {file = "pydantic_core-2.10.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:fa7db7558607afeccb33c0e4bf1c9a9a835e26599e76af6fe2fcea45904083a6"}, + {file = "pydantic_core-2.10.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:aad7bd686363d1ce4ee930ad39f14e1673248373f4a9d74d2b9554f06199fb58"}, + {file = "pydantic_core-2.10.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:443fed67d33aa85357464f297e3d26e570267d1af6fef1c21ca50921d2976302"}, + {file = "pydantic_core-2.10.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:042462d8d6ba707fd3ce9649e7bf268633a41018d6a998fb5fbacb7e928a183e"}, + {file = "pydantic_core-2.10.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:ecdbde46235f3d560b18be0cb706c8e8ad1b965e5c13bbba7450c86064e96561"}, + {file = "pydantic_core-2.10.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:ed550ed05540c03f0e69e6d74ad58d026de61b9eaebebbaaf8873e585cbb18de"}, + {file = "pydantic_core-2.10.1-cp38-none-win32.whl", hash = "sha256:8cdbbd92154db2fec4ec973d45c565e767ddc20aa6dbaf50142676484cbff8ee"}, + {file = "pydantic_core-2.10.1-cp38-none-win_amd64.whl", hash = "sha256:9f6f3e2598604956480f6c8aa24a3384dbf6509fe995d97f6ca6103bb8c2534e"}, + {file = "pydantic_core-2.10.1-cp39-cp39-macosx_10_7_x86_64.whl", hash = "sha256:655f8f4c8d6a5963c9a0687793da37b9b681d9ad06f29438a3b2326d4e6b7970"}, + {file = "pydantic_core-2.10.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:e570ffeb2170e116a5b17e83f19911020ac79d19c96f320cbfa1fa96b470185b"}, + {file = "pydantic_core-2.10.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:64322bfa13e44c6c30c518729ef08fda6026b96d5c0be724b3c4ae4da939f875"}, + {file = "pydantic_core-2.10.1-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:485a91abe3a07c3a8d1e082ba29254eea3e2bb13cbbd4351ea4e5a21912cc9b0"}, + {file = "pydantic_core-2.10.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f7c2b8eb9fc872e68b46eeaf835e86bccc3a58ba57d0eedc109cbb14177be531"}, + {file = "pydantic_core-2.10.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a5cb87bdc2e5f620693148b5f8f842d293cae46c5f15a1b1bf7ceeed324a740c"}, + {file = "pydantic_core-2.10.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:25bd966103890ccfa028841a8f30cebcf5875eeac8c4bde4fe221364c92f0c9a"}, + {file = "pydantic_core-2.10.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f323306d0556351735b54acbf82904fe30a27b6a7147153cbe6e19aaaa2aa429"}, + {file = "pydantic_core-2.10.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:0c27f38dc4fbf07b358b2bc90edf35e82d1703e22ff2efa4af4ad5de1b3833e7"}, + {file = "pydantic_core-2.10.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:f1365e032a477c1430cfe0cf2856679529a2331426f8081172c4a74186f1d595"}, + {file = "pydantic_core-2.10.1-cp39-none-win32.whl", hash = "sha256:a1c311fd06ab3b10805abb72109f01a134019739bd3286b8ae1bc2fc4e50c07a"}, + {file = "pydantic_core-2.10.1-cp39-none-win_amd64.whl", hash = "sha256:ae8a8843b11dc0b03b57b52793e391f0122e740de3df1474814c700d2622950a"}, + {file = "pydantic_core-2.10.1-pp310-pypy310_pp73-macosx_10_7_x86_64.whl", hash = "sha256:d43002441932f9a9ea5d6f9efaa2e21458221a3a4b417a14027a1d530201ef1b"}, + {file = "pydantic_core-2.10.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:fcb83175cc4936a5425dde3356f079ae03c0802bbdf8ff82c035f8a54b333521"}, + {file = "pydantic_core-2.10.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:962ed72424bf1f72334e2f1e61b68f16c0e596f024ca7ac5daf229f7c26e4208"}, + {file = "pydantic_core-2.10.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2cf5bb4dd67f20f3bbc1209ef572a259027c49e5ff694fa56bed62959b41e1f9"}, + {file = "pydantic_core-2.10.1-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e544246b859f17373bed915182ab841b80849ed9cf23f1f07b73b7c58baee5fb"}, + {file = "pydantic_core-2.10.1-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:c0877239307b7e69d025b73774e88e86ce82f6ba6adf98f41069d5b0b78bd1bf"}, + {file = "pydantic_core-2.10.1-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:53df009d1e1ba40f696f8995683e067e3967101d4bb4ea6f667931b7d4a01357"}, + {file = "pydantic_core-2.10.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:a1254357f7e4c82e77c348dabf2d55f1d14d19d91ff025004775e70a6ef40ada"}, + {file = "pydantic_core-2.10.1-pp37-pypy37_pp73-macosx_10_7_x86_64.whl", hash = "sha256:524ff0ca3baea164d6d93a32c58ac79eca9f6cf713586fdc0adb66a8cdeab96a"}, + {file = "pydantic_core-2.10.1-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3f0ac9fb8608dbc6eaf17956bf623c9119b4db7dbb511650910a82e261e6600f"}, + {file = "pydantic_core-2.10.1-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:320f14bd4542a04ab23747ff2c8a778bde727158b606e2661349557f0770711e"}, + {file = "pydantic_core-2.10.1-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:63974d168b6233b4ed6a0046296803cb13c56637a7b8106564ab575926572a55"}, + {file = "pydantic_core-2.10.1-pp37-pypy37_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:417243bf599ba1f1fef2bb8c543ceb918676954734e2dcb82bf162ae9d7bd514"}, + {file = "pydantic_core-2.10.1-pp37-pypy37_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:dda81e5ec82485155a19d9624cfcca9be88a405e2857354e5b089c2a982144b2"}, + {file = "pydantic_core-2.10.1-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:14cfbb00959259e15d684505263d5a21732b31248a5dd4941f73a3be233865b9"}, + {file = "pydantic_core-2.10.1-pp38-pypy38_pp73-macosx_10_7_x86_64.whl", hash = "sha256:631cb7415225954fdcc2a024119101946793e5923f6c4d73a5914d27eb3d3a05"}, + {file = "pydantic_core-2.10.1-pp38-pypy38_pp73-macosx_11_0_arm64.whl", hash = "sha256:bec7dd208a4182e99c5b6c501ce0b1f49de2802448d4056091f8e630b28e9a52"}, + {file = "pydantic_core-2.10.1-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:149b8a07712f45b332faee1a2258d8ef1fb4a36f88c0c17cb687f205c5dc6e7d"}, + {file = "pydantic_core-2.10.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4d966c47f9dd73c2d32a809d2be529112d509321c5310ebf54076812e6ecd884"}, + {file = "pydantic_core-2.10.1-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:7eb037106f5c6b3b0b864ad226b0b7ab58157124161d48e4b30c4a43fef8bc4b"}, + {file = "pydantic_core-2.10.1-pp38-pypy38_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:154ea7c52e32dce13065dbb20a4a6f0cc012b4f667ac90d648d36b12007fa9f7"}, + {file = "pydantic_core-2.10.1-pp38-pypy38_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:e562617a45b5a9da5be4abe72b971d4f00bf8555eb29bb91ec2ef2be348cd132"}, + {file = "pydantic_core-2.10.1-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:f23b55eb5464468f9e0e9a9935ce3ed2a870608d5f534025cd5536bca25b1402"}, + {file = "pydantic_core-2.10.1-pp39-pypy39_pp73-macosx_10_7_x86_64.whl", hash = "sha256:e9121b4009339b0f751955baf4543a0bfd6bc3f8188f8056b1a25a2d45099934"}, + {file = "pydantic_core-2.10.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:0523aeb76e03f753b58be33b26540880bac5aa54422e4462404c432230543f33"}, + {file = "pydantic_core-2.10.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2e0e2959ef5d5b8dc9ef21e1a305a21a36e254e6a34432d00c72a92fdc5ecda5"}, + {file = "pydantic_core-2.10.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:da01bec0a26befab4898ed83b362993c844b9a607a86add78604186297eb047e"}, + {file = "pydantic_core-2.10.1-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:f2e9072d71c1f6cfc79a36d4484c82823c560e6f5599c43c1ca6b5cdbd54f881"}, + {file = "pydantic_core-2.10.1-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:f36a3489d9e28fe4b67be9992a23029c3cec0babc3bd9afb39f49844a8c721c5"}, + {file = "pydantic_core-2.10.1-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:f64f82cc3443149292b32387086d02a6c7fb39b8781563e0ca7b8d7d9cf72bd7"}, + {file = "pydantic_core-2.10.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:b4a6db486ac8e99ae696e09efc8b2b9fea67b63c8f88ba7a1a16c24a057a0776"}, + {file = "pydantic_core-2.10.1.tar.gz", hash = "sha256:0f8682dbdd2f67f8e1edddcbffcc29f60a6182b4901c367fc8c1c40d30bb0a82"}, +] + +[package.dependencies] +typing-extensions = ">=4.6.0,<4.7.0 || >4.7.0" [[package]] name = "pytest" @@ -816,6 +915,7 @@ files = [ {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:69b023b2b4daa7548bcfbd4aa3da05b3a74b772db9e23b982788168117739938"}, {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81e0b275a9ecc9c0c0c07b4b90ba548307583c125f54d5b6946cfee6360c733d"}, {file = "PyYAML-6.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ba336e390cd8e4d1739f42dfe9bb83a3cc2e80f567d8805e11b46f4a943f5515"}, + {file = "PyYAML-6.0.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:326c013efe8048858a6d312ddd31d56e468118ad4cdeda36c719bf5bb6192290"}, {file = "PyYAML-6.0.1-cp310-cp310-win32.whl", hash = "sha256:bd4af7373a854424dabd882decdc5579653d7868b8fb26dc7d0e99f823aa5924"}, {file = "PyYAML-6.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:fd1592b3fdf65fff2ad0004b5e363300ef59ced41c2e6b3a99d4089fa8c5435d"}, {file = "PyYAML-6.0.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:6965a7bc3cf88e5a1c3bd2e0b5c22f8d677dc88a455344035f03399034eb3007"}, @@ -823,8 +923,15 @@ files = [ {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42f8152b8dbc4fe7d96729ec2b99c7097d656dc1213a3229ca5383f973a5ed6d"}, {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:062582fca9fabdd2c8b54a3ef1c978d786e0f6b3a1510e0ac93ef59e0ddae2bc"}, {file = "PyYAML-6.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d2b04aac4d386b172d5b9692e2d2da8de7bfb6c387fa4f801fbf6fb2e6ba4673"}, + {file = "PyYAML-6.0.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:e7d73685e87afe9f3b36c799222440d6cf362062f78be1013661b00c5c6f678b"}, {file = "PyYAML-6.0.1-cp311-cp311-win32.whl", hash = "sha256:1635fd110e8d85d55237ab316b5b011de701ea0f29d07611174a1b42f1444741"}, {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"}, + {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"}, + {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"}, + {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"}, + {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"}, + {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"}, + {file = "PyYAML-6.0.1-cp312-cp312-win_amd64.whl", hash = "sha256:0d3304d8c0adc42be59c5f8a4d9e3d7379e6955ad754aa9d6ab7a398b59dd1df"}, {file = "PyYAML-6.0.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:50550eb667afee136e9a77d6dc71ae76a44df8b3e51e41b77f6de2932bfe0f47"}, {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1fe35611261b29bd1de0070f0b2f47cb6ff71fa6595c077e42bd0c419fa27b98"}, {file = "PyYAML-6.0.1-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:704219a11b772aea0d8ecd7058d0082713c3562b4e271b849ad7dc4a5c90c13c"}, @@ -841,6 +948,7 @@ files = [ {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a0cd17c15d3bb3fa06978b4e8958dcdc6e0174ccea823003a106c7d4d7899ac5"}, {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:28c119d996beec18c05208a8bd78cbe4007878c6dd15091efb73a30e90539696"}, {file = "PyYAML-6.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7e07cbde391ba96ab58e532ff4803f79c4129397514e1413a7dc761ccd755735"}, + {file = "PyYAML-6.0.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:49a183be227561de579b4a36efbb21b3eab9651dd81b1858589f796549873dd6"}, {file = "PyYAML-6.0.1-cp38-cp38-win32.whl", hash = "sha256:184c5108a2aca3c5b3d3bf9395d50893a7ab82a38004c8f61c258d4428e80206"}, {file = "PyYAML-6.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:1e2722cc9fbb45d9b87631ac70924c11d3a401b2d7f410cc0e3bbf249f2dca62"}, {file = "PyYAML-6.0.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:9eb6caa9a297fc2c2fb8862bc5370d0303ddba53ba97e71f08023b6cd73d16a8"}, @@ -848,6 +956,7 @@ files = [ {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5773183b6446b2c99bb77e77595dd486303b4faab2b086e7b17bc6bef28865f6"}, {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b786eecbdf8499b9ca1d697215862083bd6d2a99965554781d0d8d1ad31e13a0"}, {file = "PyYAML-6.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc1bf2925a1ecd43da378f4db9e4f799775d6367bdb94671027b73b393a7c42c"}, + {file = "PyYAML-6.0.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:04ac92ad1925b2cff1db0cfebffb6ffc43457495c9b3c39d3fcae417d7125dc5"}, {file = "PyYAML-6.0.1-cp39-cp39-win32.whl", hash = "sha256:faca3bdcf85b2fc05d06ff3fbc1f83e1391b3e724afa3feba7d13eeab355484c"}, {file = "PyYAML-6.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:510c9deebc5c0225e8c96813043e62b680ba2f9c50a08d3724c7f28a747d1486"}, {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"}, @@ -929,13 +1038,13 @@ files = [ [[package]] name = "urllib3" -version = "2.0.4" +version = "2.0.5" description = "HTTP library with thread-safe connection pooling, file post, and more." optional = false python-versions = ">=3.7" files = [ - {file = "urllib3-2.0.4-py3-none-any.whl", hash = "sha256:de7df1803967d2c2a98e4b11bb7d6bd9210474c46e8a0401514e3a42a75ebde4"}, - {file = "urllib3-2.0.4.tar.gz", hash = "sha256:8d22f86aae8ef5e410d4f539fde9ce6b2113a001bb4d189e0aed70642d602b11"}, + {file = "urllib3-2.0.5-py3-none-any.whl", hash = "sha256:ef16afa8ba34a1f989db38e1dbbe0c302e4289a47856990d0682e374563ce35e"}, + {file = "urllib3-2.0.5.tar.gz", hash = "sha256:13abf37382ea2ce6fb744d4dad67838eec857c9f4f57009891805e0b5e123594"}, ] [package.extras] @@ -1050,4 +1159,4 @@ testing = ["big-O", "flake8 (<5)", "jaraco.functools", "jaraco.itertools", "more [metadata] lock-version = "2.0" python-versions = "^3.7" -content-hash = "0db2f97d52c557dd7f90c55b4ad5bbe308c957c5f7f99fec53c57e0a13822cb4" +content-hash = "b7fab8703967f2616ea59a98a437cd30f97f0c8d2a06e399d688814a2a2c64f8" diff --git a/clients/python/pyproject.toml b/clients/python/pyproject.toml index 915ac7aa..4fe6e8b0 100644 --- a/clients/python/pyproject.toml +++ b/clients/python/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "text-generation" -version = "0.6.0" +version = "0.6.1" description = "Hugging Face Text Generation Python Client" license = "Apache-2.0" authors = ["Olivier Dehaene "] diff --git a/clients/python/text_generation/types.py b/clients/python/text_generation/types.py index 6d6a0536..aa02d8d8 100644 --- a/clients/python/text_generation/types.py +++ b/clients/python/text_generation/types.py @@ -40,7 +40,7 @@ class Parameters(BaseModel): # Get decoder input token logprobs and ids decoder_input_details: bool = False # Return the N most likely tokens at each step - top_n_tokens: Optional[int] + top_n_tokens: Optional[int] = None @validator("best_of") def valid_best_of(cls, field_value, values): @@ -188,7 +188,7 @@ class BestOfSequence(BaseModel): # Generated tokens tokens: List[Token] # Most likely tokens - top_tokens: Optional[List[List[Token]]] + top_tokens: Optional[List[List[Token]]] = None # `generate` details @@ -204,7 +204,7 @@ class Details(BaseModel): # Generated tokens tokens: List[Token] # Most likely tokens - top_tokens: Optional[List[List[Token]]] + top_tokens: Optional[List[List[Token]]] = None # Additional sequences when using the `best_of` parameter best_of_sequences: Optional[List[BestOfSequence]] = None @@ -232,7 +232,7 @@ class StreamResponse(BaseModel): # Generated token token: Token # Most likely tokens - top_tokens: Optional[List[Token]] + top_tokens: Optional[List[Token]] = None # Complete generated text # Only available when the generation is finished generated_text: Optional[str] = None diff --git a/docs/source/basic_tutorials/launcher.md b/docs/source/basic_tutorials/launcher.md index a644e38b..eb34c1f6 100644 --- a/docs/source/basic_tutorials/launcher.md +++ b/docs/source/basic_tutorials/launcher.md @@ -16,6 +16,12 @@ Options: [env: REVISION=] + --validation-workers + The number of tokenizer workers used for payload validation and truncation inside the router + + [env: VALIDATION_WORKERS=] + [default: 2] + --sharded Whether to shard the model across multiple GPUs By default text-generation-inference will use all available GPUs to run the model. Setting it to `false` deactivates `num_shard` @@ -28,16 +34,23 @@ Options: [env: NUM_SHARD=] --quantize - Whether you want the model to be quantized. This will use `bitsandbytes` for quantization on the fly, or `gptq` + Whether you want the model to be quantized [env: QUANTIZE=] - [possible values: bitsandbytes, gptq] + + Possible values: + - awq: 4 bit quantization. Requires a specific GTPQ quantized model: https://hf.co/models?search=awq. Should replace GPTQ models whereever possible because of the better latency + - eetq: 8 bit quantization, doesn't require specific model. Should be a drop-in replacement to bitsandbytes with much better performance. Kernels are from https://github.com/NetEase-FuXi/EETQ.git + - gptq: 4 bit quantization. Requires a specific GTPQ quantized model: https://hf.co/models?search=gptq. text-generation-inference will use exllama (faster) kernels whereever possible, and use triton kernel (wider support) when it's not. AWQ has faster kernels + - bitsandbytes: Bitsandbytes 8bit. Can be applied on any model, will cut the memory requirement in half, but it is known that the model will be much slower to run than the native f16 + - bitsandbytes-nf4: Bitsandbytes 4bit. Can be applied on any model, will cut the memory requirement by 4x, but it is known that the model will be much slower to run than the native f16 + - bitsandbytes-fp4: Bitsandbytes 4bit. nf4 should be preferred in most cases but maybe this one has better perplexity performance for you model --dtype The dtype to be forced upon the model. This option cannot be used with `--quantize` [env: DTYPE=] - [possible values: float16, b-float16] + [possible values: float16, bfloat16] --trust-remote-code Whether you want to execute hub modelling code. Explicitly passing a `revision` is encouraged when loading a model with custom code to ensure no malicious code has been contributed in a newer revision @@ -62,6 +75,12 @@ Options: [env: MAX_STOP_SEQUENCES=] [default: 4] + --max-top-n-tokens + This is the maximum allowed value for clients to set `top_n_tokens`. `top_n_tokens is used to return information about the the `n` most likely tokens at each generation step, instead of just the sampled token. This information can be used for downstream tasks like for classification or ranking + + [env: MAX_TOP_N_TOKENS=] + [default: 5] + --max-input-length This is the maximum allowed input length (expressed in number of tokens) for users. The larger this value, the longer prompt users can send which can impact the overall memory required to handle the load. Please note that some models have a finite range of sequence they can handle @@ -100,7 +119,6 @@ Options: Overall this number should be the largest possible amount that fits the remaining memory (after the model is loaded). Since the actual memory overhead depends on other parameters like if you're using quantization, flash attention or the model implementation, text-generation-inference cannot infer this number automatically. [env: MAX_BATCH_TOTAL_TOKENS=] - [default: 16000] --max-waiting-tokens This setting defines how many tokens can be passed before forcing the waiting queries to be put on the batch (if the size of the batch allows for it). New queries require 1 `prefill` forward, which is different from `decode` and therefore you need to pause the running batch in order to run `prefill` to create the correct values for the waiting queries to be able to join the batch. @@ -114,6 +132,12 @@ Options: [env: MAX_WAITING_TOKENS=] [default: 20] + --hostname + The IP address to listen on + + [env: HOSTNAME=] + [default: 0.0.0.0] + -p, --port The port to listen on @@ -153,6 +177,29 @@ Options: [env: DISABLE_CUSTOM_KERNELS=] + --cuda-memory-fraction + Limit the CUDA available memory. The allowed value equals the total visible memory multiplied by cuda-memory-fraction + + [env: CUDA_MEMORY_FRACTION=] + [default: 1.0] + + --rope-scaling + Rope scaling will only be used for RoPE models and allow rescaling the position rotary to accomodate for larger prompts. + + Goes together with `rope_factor`. + + `--rope-factor 2.0` gives linear scaling with a factor of 2.0 `--rope-scaling dynamic` gives dynamic scaling with a factor of 1.0 `--rope-scaling linear` gives linear scaling with a factor of 1.0 (Nothing will be changed basically) + + `--rope-scaling linear --rope-factor` fully describes the scaling you want + + [env: ROPE_SCALING=] + [possible values: linear, dynamic] + + --rope-factor + Rope scaling will only be used for RoPE models See `rope_scaling` + + [env: ROPE_FACTOR=] + --json-output Outputs the logs in JSON format (useful for telemetry) @@ -180,20 +227,10 @@ Options: [env: NGROK_AUTHTOKEN=] - --ngrok-domain - ngrok domain name where the axum webserver will be available at + --ngrok-edge + ngrok edge - [env: NGROK_DOMAIN=] - - --ngrok-username - ngrok basic auth username - - [env: NGROK_USERNAME=] - - --ngrok-password - ngrok basic auth password - - [env: NGROK_PASSWORD=] + [env: NGROK_EDGE=] -e, --env Display a lot of information about your runtime environment