transformers/conftest.py

143 lines
5.1 KiB
Python
Raw Normal View History

# Copyright 2020 The HuggingFace Team. All rights reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# tests directory-specific settings - this file is run automatically
# by pytest before any tests are run
import doctest
import sys
2020-09-14 19:50:51 +08:00
import warnings
from os.path import abspath, dirname, join
import _pytest
import pytest
from transformers.testing_utils import HfDoctestModule, HfDocTestParser
NOT_DEVICE_TESTS = {
"test_tokenization",
"test_processor",
"test_processing",
"test_beam_constraints",
"test_configuration_utils",
"test_data_collator",
"test_trainer_callback",
"test_trainer_utils",
"test_feature_extraction",
"test_image_processing",
"test_image_processor",
"test_image_transforms",
"test_optimization",
"test_retrieval",
"test_config",
"test_from_pretrained_no_checkpoint",
"test_keep_in_fp32_modules",
"test_gradient_checkpointing_backward_compatibility",
"test_gradient_checkpointing_enable_disable",
"test_save_load_fast_init_from_base",
"test_fast_init_context_manager",
"test_fast_init_tied_embeddings",
"test_save_load_fast_init_to_base",
"test_torch_save_load",
"test_initialization",
"test_forward_signature",
"test_model_common_attributes",
"test_model_main_input_name",
"test_correct_missing_keys",
"test_tie_model_weights",
"test_can_use_safetensors",
"test_load_save_without_tied_weights",
"test_tied_weights_keys",
"test_model_weights_reload_no_missing_tied_weights",
"test_pt_tf_model_equivalence",
"test_mismatched_shapes_have_properly_initialized_weights",
"test_matched_shapes_have_loaded_weights_when_some_mismatched_shapes_exist",
"test_model_is_small",
"test_tf_from_pt_safetensors",
"test_flax_from_pt_safetensors",
"ModelTest::test_pipeline_", # None of the pipeline tests from PipelineTesterMixin (of which XxxModelTest inherits from) are running on device
"ModelTester::test_pipeline_",
"/repo_utils/",
"/utils/",
"/tools/",
}
# allow having multiple repository checkouts and not needing to remember to rerun
# `pip install -e '.[dev]'` when switching between checkouts and running tests.
git_repo_path = abspath(join(dirname(__file__), "src"))
sys.path.insert(1, git_repo_path)
2020-09-14 19:50:51 +08:00
# silence FutureWarning warnings in tests since often we can't act on them until
# they become normal warnings - i.e. the tests still need to test the current functionality
warnings.simplefilter(action="ignore", category=FutureWarning)
def pytest_configure(config):
config.addinivalue_line(
"markers", "is_pt_tf_cross_test: mark test to run only when PT and TF interactions are tested"
)
config.addinivalue_line(
"markers", "is_pt_flax_cross_test: mark test to run only when PT and FLAX interactions are tested"
)
config.addinivalue_line("markers", "is_pipeline_test: mark test to run only when pipelines are tested")
config.addinivalue_line("markers", "is_staging_test: mark test to run only in the staging environment")
config.addinivalue_line("markers", "accelerate_tests: mark test that require accelerate")
Test composition (#23214) * Remove nestedness in tool config * Really do it * Use remote tools descriptions * Work * Clean up eval * Changes * Tools * Tools * tool * Fix everything * Use last result/assign for evaluation * Prompt * Remove hardcoded selection * Evaluation for chat agents * correct some spelling * Small fixes * Change summarization model (#23172) * Fix link displayed * Update description of the tool * Fixes in chat prompt * Custom tools, custom prompt * Tool clean up * save_pretrained and push_to_hub for tool * Fix init * Tests * Fix tests * Tool save/from_hub/push_to_hub and tool->load_tool * Clean push_to_hub and add app file * Custom inference API for endpoints too * Clean up * old remote tool and new remote tool * Make a requirements * return_code adds tool creation * Avoid redundancy between global variables * Remote tools can be loaded * Tests * Text summarization tests * Quality * Properly mark tests * Test the python interpreter * And the CI shall be green. * fix loading of additional tools * Work on RemoteTool and fix tests * General clean up * Guard imports * Fix tools * docs: Fix broken link in 'How to add a model...' (#23216) fix link * Get default endpoint from the Hub * Add guide * Simplify tool config * Docs * Some fixes * Docs * Docs * Docs * Fix code returned by agent * Try this * Match args with signature in remote tool * Should fix python interpreter for Python 3.8 * Fix push_to_hub for tools * Other fixes to push_to_hub * Add API doc page * Docs * Docs * Custom tools * Pin tensorflow-probability (#23220) * Pin tensorflow-probability * [all-test] * [all-test] Fix syntax for bash * PoC for some chaining API * Text to speech * J'ai pris des libertés * Rename * Basic python interpreter * Add agents * Quality * Add translation tool * temp * GenQA + LID + S2T * Quality + word missing in translation * Add open assistance, support f-strings in evaluate * captioning + s2t fixes * Style * Refactor descriptions and remove chain * Support errors and rename OpenAssistantAgent * Add setup * Deal with typos + example of inference API * Some rename + README * Fixes * Update prompt * Unwanted change * Make sure everyone has a default * One prompt to rule them all. * SD * Description * Clean up remote tools * More remote tools * Add option to return code and update doc * Image segmentation * ControlNet * Gradio demo * Diffusers protection * Lib protection * ControlNet description * Cleanup * Style * Remove accelerate and try to be reproducible * No randomness * Male Basic optional in token * Clean description * Better prompts * Fix args eval in interpreter * Add tool wrapper * Tool on the Hub * Style post-rebase * Big refactor of descriptions, batch generation and evaluation for agents * Make problems easier - interface to debug * More problems, add python primitives * Back to one prompt * Remove dict for translation * Be consistent * Add prompts * New version of the agent * Evaluate new agents * New endpoints agents * Make all tools a dict variable * Typo * Add problems * Add to big prompt * Harmonize * Add tools * New evaluation * Add more tools * Build prompt with tools descriptions * Tools on the Hub * Let's chat! * Cleanup * Temporary bs4 safeguard * Cache agents and clean up * Blank init * Fix evaluation for agents * New format for tools on the Hub * Add method to reset state * Remove nestedness in tool config * Really do it * Use remote tools descriptions * Work * Clean up eval * Changes * Tools * Tools * tool * Fix everything * Use last result/assign for evaluation * Prompt * Remove hardcoded selection * Evaluation for chat agents * correct some spelling * Small fixes * Change summarization model (#23172) * Fix link displayed * Update description of the tool * Fixes in chat prompt * Custom tools, custom prompt * Tool clean up * save_pretrained and push_to_hub for tool * Fix init * Tests * Fix tests * Tool save/from_hub/push_to_hub and tool->load_tool * Clean push_to_hub and add app file * Custom inference API for endpoints too * Clean up * old remote tool and new remote tool * Make a requirements * return_code adds tool creation * Avoid redundancy between global variables * Remote tools can be loaded * Tests * Text summarization tests * Quality * Properly mark tests * Test the python interpreter * And the CI shall be green. * Work on RemoteTool and fix tests * fix loading of additional tools * General clean up * Guard imports * Fix tools * Get default endpoint from the Hub * Simplify tool config * Add guide * Docs * Some fixes * Docs * Docs * Fix code returned by agent * Try this * Docs * Match args with signature in remote tool * Should fix python interpreter for Python 3.8 * Fix push_to_hub for tools * Other fixes to push_to_hub * Add API doc page * Fixes * Doc fixes * Docs * Fix audio * Custom tools * Audio fix * Improve custom tools docstring * Docstrings * Trigger CI * Mode docstrings * More docstrings * Improve custom tools * Fix for remote tools * Style * Fix repo consistency * Quality * Tip * Cleanup on doc * Cleanup toc * Add disclaimer for starcoder vs openai * Remove disclaimer * Small fixed in the prompts * 4.29 * Update src/transformers/tools/agents.py Co-authored-by: Lysandre Debut <lysandre.debut@reseau.eseo.fr> * Complete documentation * Small fixes * Agent evaluation * Note about gradio-tools & LC * Clean up agents and prompt * Apply suggestions from code review Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Apply suggestions from code review Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> * Note about gradio-tools & LC * Add copyrights and address review comments * Quality * Add all language codes * Add remote tool tests * Move custom prompts to other docs * Apply suggestions from code review Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com> * TTS tests * Quality --------- Co-authored-by: Lysandre <hi@lyand.re> Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com> Co-authored-by: Philipp Schmid <32632186+philschmid@users.noreply.github.com> Co-authored-by: Connor Henderson <connor.henderson@talkiatry.com> Co-authored-by: Lysandre <lysandre.debut@reseau.eseo.fr> Co-authored-by: Lysandre <lysandre@huggingface.co> Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
2023-05-10 08:37:57 +08:00
config.addinivalue_line("markers", "tool_tests: mark the tool tests that are run on their specific schedule")
config.addinivalue_line("markers", "not_device_test: mark the tests always running on cpu")
def pytest_collection_modifyitems(items):
for item in items:
if any(test_name in item.nodeid for test_name in NOT_DEVICE_TESTS):
item.add_marker(pytest.mark.not_device_test)
def pytest_addoption(parser):
from transformers.testing_utils import pytest_addoption_shared
pytest_addoption_shared(parser)
def pytest_terminal_summary(terminalreporter):
from transformers.testing_utils import pytest_terminal_summary_main
make_reports = terminalreporter.config.getoption("--make-reports")
if make_reports:
pytest_terminal_summary_main(terminalreporter, id=make_reports)
def pytest_sessionfinish(session, exitstatus):
# If no tests are collected, pytest exists with code 5, which makes the CI fail.
if exitstatus == 5:
session.exitstatus = 0
# Doctest custom flag to ignore output.
IGNORE_RESULT = doctest.register_optionflag("IGNORE_RESULT")
OutputChecker = doctest.OutputChecker
class CustomOutputChecker(OutputChecker):
def check_output(self, want, got, optionflags):
if IGNORE_RESULT & optionflags:
return True
return OutputChecker.check_output(self, want, got, optionflags)
doctest.OutputChecker = CustomOutputChecker
_pytest.doctest.DoctestModule = HfDoctestModule
doctest.DocTestParser = HfDocTestParser