SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Use HF_HUB_OFFLINE + fix has_file in offline mode (#31016)

Browse Source 
* Fix has_file in offline mode

* harmonize env variable for offline mode

* Switch to HF_HUB_OFFLINE

* fix test

* revert test_offline to test TRANSFORMERS_OFFLINE

* Add new offline test

* merge conflicts

* docs
This commit is contained in:
Lucain
2024-05-29 12:55:43 +02:00
committed by GitHub
parent bfe6f513b9
commit c3044ec2f3
16 changed files with 148 additions and 76 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
tests/utils/test_hub_utils.py
View File

@@ -18,6 +18,7 @@ import unittest
import unittest.mock as mock
from pathlib import Path
from huggingface_hub import hf_hub_download
from requests.exceptions import HTTPError
from transformers.utils import (
@@ -33,6 +34,7 @@ from transformers.utils import (
RANDOM_BERT = "hf-internal-testing/tiny-random-bert"
TINY_BERT_PT_ONLY = "hf-internal-testing/tiny-bert-pt-only"
CACHE_DIR = os.path.join(TRANSFORMERS_CACHE, "models--hf-internal-testing--tiny-random-bert")
FULL_COMMIT_HASH = "9b8c223d42b2188cb49d29af482996f9d0f3e5a6"
@@ -99,9 +101,20 @@ class GetFromCacheTests(unittest.TestCase):
mock_head.assert_called()
def test_has_file(self):
self.assertTrue(has_file("hf-internal-testing/tiny-bert-pt-only", WEIGHTS_NAME))
self.assertFalse(has_file("hf-internal-testing/tiny-bert-pt-only", TF2_WEIGHTS_NAME))
self.assertFalse(has_file("hf-internal-testing/tiny-bert-pt-only", FLAX_WEIGHTS_NAME))
self.assertTrue(has_file(TINY_BERT_PT_ONLY, WEIGHTS_NAME))
self.assertFalse(has_file(TINY_BERT_PT_ONLY, TF2_WEIGHTS_NAME))
self.assertFalse(has_file(TINY_BERT_PT_ONLY, FLAX_WEIGHTS_NAME))
def test_has_file_in_cache(self):
with tempfile.TemporaryDirectory() as tmp_dir:
# Empty cache dir + offline mode => return False
assert not has_file(TINY_BERT_PT_ONLY, WEIGHTS_NAME, local_files_only=True, cache_dir=tmp_dir)
# Populate cache dir
hf_hub_download(TINY_BERT_PT_ONLY, WEIGHTS_NAME, cache_dir=tmp_dir)
# Cache dir + offline mode => return True
assert has_file(TINY_BERT_PT_ONLY, WEIGHTS_NAME, local_files_only=True, cache_dir=tmp_dir)
def test_get_file_from_repo_distant(self):
# `get_file_from_repo` returns None if the file does not exist

103
tests/utils/test_offline.py
View File

@@ -14,6 +14,7 @@
import subprocess
import sys
from typing import Tuple
from transformers import BertConfig, BertModel, BertTokenizer, pipeline
from transformers.testing_utils import TestCasePlus, require_torch
@@ -56,15 +57,9 @@ socket.socket = offline_socket
pipeline(task="fill-mask", model=mname)
# baseline - just load from_pretrained with normal network
cmd = [sys.executable, "-c", "\n".join([load, run, mock])]
# should succeed
env = self.get_env()
# should succeed as TRANSFORMERS_OFFLINE=1 tells it to use local files
env["TRANSFORMERS_OFFLINE"] = "1"
result = subprocess.run(cmd, env=env, check=False, capture_output=True)
self.assertEqual(result.returncode, 0, result.stderr)
self.assertIn("success", result.stdout.decode())
stdout, _ = self._execute_with_env(load, run, mock, TRANSFORMERS_OFFLINE="1")
self.assertIn("success", stdout)
@require_torch
def test_offline_mode_no_internet(self):
@@ -97,13 +92,9 @@ socket.socket = offline_socket
pipeline(task="fill-mask", model=mname)
# baseline - just load from_pretrained with normal network
cmd = [sys.executable, "-c", "\n".join([load, run, mock])]
# should succeed
env = self.get_env()
result = subprocess.run(cmd, env=env, check=False, capture_output=True)
self.assertEqual(result.returncode, 0, result.stderr)
self.assertIn("success", result.stdout.decode())
stdout, _ = self._execute_with_env(load, run, mock)
self.assertIn("success", stdout)
@require_torch
def test_offline_mode_sharded_checkpoint(self):
@@ -132,27 +123,17 @@ socket.socket = offline_socket
"""
# baseline - just load from_pretrained with normal network
cmd = [sys.executable, "-c", "\n".join([load, run])]
# should succeed
env = self.get_env()
result = subprocess.run(cmd, env=env, check=False, capture_output=True)
self.assertEqual(result.returncode, 0, result.stderr)
self.assertIn("success", result.stdout.decode())
stdout, _ = self._execute_with_env(load, run)
self.assertIn("success", stdout)
# next emulate no network
cmd = [sys.executable, "-c", "\n".join([load, mock, run])]
# Doesn't fail anymore since the model is in the cache due to other tests, so commenting this.
# env["TRANSFORMERS_OFFLINE"] = "0"
# result = subprocess.run(cmd, env=env, check=False, capture_output=True)
# self.assertEqual(result.returncode, 1, result.stderr)
# self._execute_with_env(load, mock, run, should_fail=True, TRANSFORMERS_OFFLINE="0")
# should succeed as TRANSFORMERS_OFFLINE=1 tells it to use local files
env["TRANSFORMERS_OFFLINE"] = "1"
result = subprocess.run(cmd, env=env, check=False, capture_output=True)
self.assertEqual(result.returncode, 0, result.stderr)
self.assertIn("success", result.stdout.decode())
stdout, _ = self._execute_with_env(load, mock, run, TRANSFORMERS_OFFLINE="1")
self.assertIn("success", stdout)
@require_torch
def test_offline_mode_pipeline_exception(self):
@@ -169,14 +150,11 @@ import socket
def offline_socket(*args, **kwargs): raise socket.error("Offline mode is enabled")
socket.socket = offline_socket
"""
env = self.get_env()
env["TRANSFORMERS_OFFLINE"] = "1"
cmd = [sys.executable, "-c", "\n".join([load, mock, run])]
result = subprocess.run(cmd, env=env, check=False, capture_output=True)
self.assertEqual(result.returncode, 1, result.stderr)
_, stderr = self._execute_with_env(load, mock, run, should_fail=True, TRANSFORMERS_OFFLINE="1")
self.assertIn(
"You cannot infer task automatically within `pipeline` when using offline mode",
result.stderr.decode().replace("\n", ""),
stderr.replace("\n", ""),
)
@require_torch
@@ -191,16 +169,51 @@ print("success")
"""
# baseline - just load from_pretrained with normal network
cmd = [sys.executable, "-c", "\n".join([load, run])]
# should succeed
env = self.get_env()
result = subprocess.run(cmd, env=env, check=False, capture_output=True)
self.assertEqual(result.returncode, 0, result.stderr)
self.assertIn("success", result.stdout.decode())
stdout, _ = self._execute_with_env(load, run)
self.assertIn("success", stdout)
# should succeed as TRANSFORMERS_OFFLINE=1 tells it to use local files
env["TRANSFORMERS_OFFLINE"] = "1"
result = subprocess.run(cmd, env=env, check=False, capture_output=True)
self.assertEqual(result.returncode, 0, result.stderr)
self.assertIn("success", result.stdout.decode())
stdout, _ = self._execute_with_env(load, run, TRANSFORMERS_OFFLINE="1")
self.assertIn("success", stdout)
def test_is_offline_mode(self):
"""
Test `_is_offline_mode` helper (should respect both HF_HUB_OFFLINE and legacy TRANSFORMERS_OFFLINE env vars)
"""
load = "from transformers.utils import is_offline_mode"
run = "print(is_offline_mode())"
stdout, _ = self._execute_with_env(load, run)
self.assertIn("False", stdout)
stdout, _ = self._execute_with_env(load, run, TRANSFORMERS_OFFLINE="1")
self.assertIn("True", stdout)
stdout, _ = self._execute_with_env(load, run, HF_HUB_OFFLINE="1")
self.assertIn("True", stdout)
def _execute_with_env(self, *commands: Tuple[str, ...], should_fail: bool = False, **env) -> Tuple[str, str]:
"""Execute Python code with a given environment and return the stdout/stderr as strings.
If `should_fail=True`, the command is expected to fail. Otherwise, it should succeed.
Environment variables can be passed as keyword arguments.
"""
# Build command
cmd = [sys.executable, "-c", "\n".join(commands)]
# Configure env
new_env = self.get_env()
new_env.update(env)
# Run command
result = subprocess.run(cmd, env=new_env, check=False, capture_output=True)
# Check execution
if should_fail:
self.assertNotEqual(result.returncode, 0, result.stderr)
else:
self.assertEqual(result.returncode, 0, result.stderr)
# Return output
return result.stdout.decode(), result.stderr.decode()