From be9b0e852126bad6b5814eb0d5e5a9e0669d312c Mon Sep 17 00:00:00 2001 From: Joao Gante Date: Wed, 23 Apr 2025 14:45:00 +0100 Subject: [PATCH] [CI] add back `sacrebleu` (and document why) (#37700) * example test * add back dep * dev-ci * dev-ci --- setup.py | 5 +++++ src/transformers/dependency_versions_table.py | 1 + 2 files changed, 6 insertions(+) diff --git a/setup.py b/setup.py index 40efb04b35..60080a2358 100644 --- a/setup.py +++ b/setup.py @@ -163,6 +163,10 @@ _deps = [ "rjieba", "rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1", "ruff==0.11.2", + # `sacrebleu` not used in `transformers`. However, it is needed in several tests, when a test calls + # `evaluate.load("sacrebleu")`. This metric is used in the examples that we use to test the `Trainer` with, in the + # `Trainer` tests (see references to `run_translation.py`). + "sacrebleu>=1.4.12,<2.0.0", "sacremoses", "safetensors>=0.4.3", "sagemaker>=2.31.0", @@ -352,6 +356,7 @@ extras["testing"] = ( "tensorboard", "pydantic", "sentencepiece", + "sacrebleu", # needed in trainer tests, see references to `run_translation.py` ) + extras["retrieval"] + extras["modelcreation"] diff --git a/src/transformers/dependency_versions_table.py b/src/transformers/dependency_versions_table.py index 84b29b5010..0a57b11a53 100644 --- a/src/transformers/dependency_versions_table.py +++ b/src/transformers/dependency_versions_table.py @@ -69,6 +69,7 @@ deps = { "rjieba": "rjieba", "rouge-score": "rouge-score!=0.0.7,!=0.0.8,!=0.1,!=0.1.1", "ruff": "ruff==0.11.2", + "sacrebleu": "sacrebleu>=1.4.12,<2.0.0", "sacremoses": "sacremoses", "safetensors": "safetensors>=0.4.3", "sagemaker": "sagemaker>=2.31.0",