Files
axolotl/tests/hf_offline_utils.py
Wing Lian fc4e37920b transformers v5 upgrade (#3272)
* Prepare for transformers v5 upgrade

* fix hf cli

* update for hf hub changes

* fix tokenizer apply_chat_template args

* remap include_tokens_per_second

* fix tps

* handle migration for warmup

* use latest hf hub

* Fix scan -> ls

* fix import

* fix for renaming of mistral common tokenizer -> backend

* update for fixed tokenziation for llama

* Skip phi35 tests for now

* remove mistral patch fixed upstream in huggingface/transformers#41439

* use namespacing for patch

* don't rely on sdist for e2e tests for now

* run modal ci without waiting too

* Fix dep for ci

* fix imports

* Fix fp8 check

* fsdp2 fixes

* fix version handling

* update fsdp version tests for new v5 behavior

* Fail multigpu tests after 3 failures

* skip known v5 broken tests for now and cleanup

* bump deps

* unmark skipped test

* re-enable test_fsdp_qlora_prequant_packed test

* increase multigpu ci timeout

* skip broken gemma3 test

* reduce timout back to original 120min now that the hanging test is skipped

* fix for un-necessary collator for pretraining with bsz=1

* fix: safe_serialization deprecated in transformers v5 rc01 (#3318)

* torch_dtype deprecated

* load model in float32 for consistency with tests

* revert some test fixtures back

* use hf cache ls instead of scan

* don't strip fsdp_version

more fdsp_Version fixes for v5
fix version in fsdp_config
fix aliasing
fix fsdp_version check
check fsdp_version is 2 in both places

* Transformers v5 rc2 (#3347)

* bump dep

* use latest fbgemm, grab model config as part of fixture, un-skip test

* import AutoConfig

* don't need more problematic autoconfig when specifying config.json manually

* add fixtures for argilla ultrafeedback datasets

* download phi4-reasoning

* fix arg

* update tests for phi fast tokenizer changes

* use explicit model types for gemma3

---------

Co-authored-by: Wing Lian <wing@axolotl.ai>

* fix: AutoModelForVision2Seq -> AutoModelForImageTextToText

* chore: remove duplicate

* fix: attempt fix gemma3 text mode

* chore: lint

* ga release of v5

* need property setter for name_or_path for mistral tokenizer

* vllm not compatible with transformers v5

* setter for chat_template w mistral too

---------

Co-authored-by: NanoCode012 <nano@axolotl.ai>
Co-authored-by: salman <salman.mohammadi@outlook.com>
2026-01-27 17:08:24 -05:00

105 lines
3.3 KiB
Python

"""
test utils for helpers and decorators
"""
import os
from contextlib import contextmanager
from functools import wraps
def reload_modules(hf_hub_offline):
# Force reload of the modules that check this variable
import importlib
import datasets
import huggingface_hub.constants
# from huggingface_hub.utils import reset_sessions
# Reload the constants module first, as others depend on it
importlib.reload(huggingface_hub.constants)
huggingface_hub.constants.HF_HUB_OFFLINE = hf_hub_offline
importlib.reload(datasets.config)
datasets.config.HF_HUB_OFFLINE = hf_hub_offline
def enable_hf_offline(test_func):
"""
test decorator that sets HF_HUB_OFFLINE environment variable to True and restores it after the test even if the test fails.
:param test_func:
:return:
"""
@wraps(test_func)
def wrapper(*args, **kwargs):
# Save the original value of HF_HUB_OFFLINE environment variable
original_hf_offline = os.getenv("HF_HUB_OFFLINE")
# Set HF_OFFLINE environment variable to True
os.environ["HF_HUB_OFFLINE"] = "1"
reload_modules(True)
try:
# Run the test function
return test_func(*args, **kwargs)
finally:
# Restore the original value of HF_HUB_OFFLINE environment variable
if original_hf_offline is not None:
os.environ["HF_HUB_OFFLINE"] = original_hf_offline
reload_modules(bool(original_hf_offline))
else:
del os.environ["HF_HUB_OFFLINE"]
reload_modules(False)
return wrapper
def disable_hf_offline(test_func):
"""
test decorator that sets HF_HUB_OFFLINE environment variable to False and restores it after the wrapped func
:param test_func:
:return:
"""
@wraps(test_func)
def wrapper(*args, **kwargs):
# Save the original value of HF_HUB_OFFLINE environment variable
original_hf_offline = os.getenv("HF_HUB_OFFLINE")
# Set HF_OFFLINE environment variable to True
os.environ["HF_HUB_OFFLINE"] = "0"
reload_modules(False)
try:
# Run the test function
return test_func(*args, **kwargs)
finally:
# Restore the original value of HF_HUB_OFFLINE environment variable
if original_hf_offline is not None:
os.environ["HF_HUB_OFFLINE"] = original_hf_offline
reload_modules(bool(original_hf_offline))
else:
del os.environ["HF_HUB_OFFLINE"]
reload_modules(False)
return wrapper
@contextmanager
def hf_offline_context(hf_hub_offline):
"""
Context manager that sets HF_HUB_OFFLINE environment variable to the given value.
:param hf_hub_offline: The new value for HF_HUB_OFFLINE.
:return: A context manager.
"""
original_hf_offline = os.getenv("HF_HUB_OFFLINE")
os.environ["HF_HUB_OFFLINE"] = str(hf_hub_offline)
reload_modules(bool(hf_hub_offline))
yield
# Restore the original value of HF_HUB_OFFLINE environment variable
if original_hf_offline is not None:
os.environ["HF_HUB_OFFLINE"] = original_hf_offline
reload_modules(bool(original_hf_offline))
else:
del os.environ["HF_HUB_OFFLINE"]
reload_modules(False)