File size: 10,411 Bytes
a9bd396
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
import os

import requests
from huggingface_hub import hf_hub_download, snapshot_download

from transformers.testing_utils import _run_pipeline_tests, _run_staging
from transformers.utils.import_utils import is_mistral_common_available


URLS_FOR_TESTING_DATA = [
    "http://images.cocodataset.org/val2017/000000000139.jpg",
    "http://images.cocodataset.org/val2017/000000000285.jpg",
    "http://images.cocodataset.org/val2017/000000000632.jpg",
    "http://images.cocodataset.org/val2017/000000000724.jpg",
    "http://images.cocodataset.org/val2017/000000000776.jpg",
    "http://images.cocodataset.org/val2017/000000000785.jpg",
    "http://images.cocodataset.org/val2017/000000000802.jpg",
    "http://images.cocodataset.org/val2017/000000000872.jpg",
    "http://images.cocodataset.org/val2017/000000039769.jpg",
    "https://cdn.britannica.com/59/94459-050-DBA42467/Skyline-Chicago.jpg",
    "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg",
    "https://huggingface.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3",
    "https://huggingface.co/datasets/hf-internal-testing/fixtures-captioning/resolve/main/bus.png",
    "https://huggingface.co/datasets/hf-internal-testing/fixtures_videos/resolve/main/tennis.mp4",
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/coco_sample.png",
    "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/tasks/australia.jpg",
    "https://huggingface.co/datasets/raushan-testing-hf/audio-test/resolve/main/f2641_0_throatclearing.wav",
    "https://huggingface.co/datasets/raushan-testing-hf/audio-test/resolve/main/glass-breaking-151256.mp3",
    "https://huggingface.co/datasets/raushan-testing-hf/images_test/resolve/main/picsum_237_200x300.jpg",
    "https://huggingface.co/datasets/raushan-testing-hf/videos-test/resolve/main/Big_Buck_Bunny_720_10s_10MB.mp4",
    "https://huggingface.co/datasets/raushan-testing-hf/videos-test/resolve/main/sample_demo_1.mp4",
    "https://huggingface.co/microsoft/kosmos-2.5/resolve/main/receipt_00008.png",
    "https://huggingface.co/microsoft/kosmos-2-patch14-224/resolve/main/two_dogs.jpg",
    "https://llava-vl.github.io/static/images/view.jpg",
    "https://huggingface.co/datasets/hf-internal-testing/fixtures_videos/resolve/main/tennis.mp4",
    "https://huggingface.co/datasets/raushan-testing-hf/videos-test/resolve/main/tiny_video.mp4",
    "https://thumbs.dreamstime.com/b/golden-gate-bridge-san-francisco-purple-flowers-california-echium-candicans-36805947.jpg",
    "https://huggingface.co/datasets/raushan-testing-hf/videos-test/resolve/main/tiny_video.mp4",
]


def url_to_local_path(url, return_url_if_not_found=True):
    filename = url.split("/")[-1]

    if not os.path.exists(filename) and return_url_if_not_found:
        return url

    return filename


if __name__ == "__main__":
    if _run_pipeline_tests:
        import datasets

        _ = datasets.load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
        _ = datasets.load_dataset("hf-internal-testing/fixtures_image_utils", split="test", revision="refs/pr/1")
        _ = hf_hub_download(repo_id="nateraw/video-demo", filename="archery.mp4", repo_type="dataset")

        hf_hub_download("Narsil/asr_dummy", filename="hindi.ogg", repo_type="dataset")
        hf_hub_download(repo_id="hf-internal-testing/bool-masked-pos", filename="bool_masked_pos.pt")
        hf_hub_download(
            repo_id="hf-internal-testing/fixtures_docvqa",
            filename="nougat_pdf.png",
            repo_type="dataset",
            revision="ec57bf8c8b1653a209c13f6e9ee66b12df0fc2db",
        )
        hf_hub_download(
            repo_id="hf-internal-testing/image-matting-fixtures", filename="image.png", repo_type="dataset"
        )
        hf_hub_download(
            repo_id="hf-internal-testing/image-matting-fixtures", filename="trimap.png", repo_type="dataset"
        )
        hf_hub_download(
            repo_id="hf-internal-testing/spaghetti-video", filename="eating_spaghetti.npy", repo_type="dataset"
        )
        hf_hub_download(
            repo_id="hf-internal-testing/spaghetti-video",
            filename="eating_spaghetti_32_frames.npy",
            repo_type="dataset",
        )
        hf_hub_download(
            repo_id="hf-internal-testing/spaghetti-video",
            filename="eating_spaghetti_8_frames.npy",
            repo_type="dataset",
        )
        hf_hub_download(
            repo_id="hf-internal-testing/tourism-monthly-batch", filename="train-batch.pt", repo_type="dataset"
        )
        hf_hub_download(repo_id="huggyllama/llama-7b", filename="tokenizer.model")
        hf_hub_download(
            repo_id="nielsr/audio-spectogram-transformer-checkpoint", filename="sample_audio.flac", repo_type="dataset"
        )
        hf_hub_download(repo_id="nielsr/example-pdf", repo_type="dataset", filename="example_pdf.png")
        hf_hub_download(
            repo_id="nielsr/test-image",
            filename="llava_1_6_input_ids.pt",
            repo_type="dataset",
        )
        hf_hub_download(
            repo_id="nielsr/test-image",
            filename="llava_1_6_pixel_values.pt",
            repo_type="dataset",
        )
        hf_hub_download(repo_id="nielsr/textvqa-sample", filename="bus.png", repo_type="dataset")
        hf_hub_download(
            repo_id="raushan-testing-hf/images_test",
            filename="emu3_image.npy",
            repo_type="dataset",
        )
        hf_hub_download(repo_id="raushan-testing-hf/images_test", filename="llava_v1_5_radar.jpg", repo_type="dataset")
        hf_hub_download(repo_id="raushan-testing-hf/videos-test", filename="sample_demo_1.mp4", repo_type="dataset")
        hf_hub_download(repo_id="raushan-testing-hf/videos-test", filename="video_demo.npy", repo_type="dataset")
        hf_hub_download(repo_id="raushan-testing-hf/videos-test", filename="video_demo_2.npy", repo_type="dataset")
        hf_hub_download(
            repo_id="shumingh/perception_lm_test_images",
            filename="14496_0.PNG",
            repo_type="dataset",
        )
        hf_hub_download(
            repo_id="shumingh/perception_lm_test_videos",
            filename="GUWR5TyiY-M_000012_000022.mp4",
            repo_type="dataset",
        )
        repo_id = "nielsr/image-segmentation-toy-data"
        hf_hub_download(
            repo_id="nielsr/image-segmentation-toy-data",
            filename="instance_segmentation_image_1.png",
            repo_type="dataset",
        )
        hf_hub_download(
            repo_id="nielsr/image-segmentation-toy-data",
            filename="instance_segmentation_image_2.png",
            repo_type="dataset",
        )
        hf_hub_download(
            repo_id="nielsr/image-segmentation-toy-data",
            filename="instance_segmentation_annotation_1.png",
            repo_type="dataset",
        )
        hf_hub_download(
            repo_id="nielsr/image-segmentation-toy-data",
            filename="instance_segmentation_annotation_2.png",
            repo_type="dataset",
        )
        hf_hub_download(
            repo_id="nielsr/image-segmentation-toy-data",
            filename="semantic_segmentation_annotation_1.png",
            repo_type="dataset",
        )
        hf_hub_download(
            repo_id="nielsr/image-segmentation-toy-data",
            filename="semantic_segmentation_annotation_2.png",
            repo_type="dataset",
        )
        hf_hub_download(
            repo_id="nielsr/image-segmentation-toy-data",
            filename="semantic_segmentation_image_1.png",
            repo_type="dataset",
        )
        hf_hub_download(
            repo_id="nielsr/image-segmentation-toy-data",
            filename="semantic_segmentation_image_2.png",
            repo_type="dataset",
        )
        hf_hub_download("shi-labs/oneformer_demo", "ade20k_panoptic.json", repo_type="dataset")

        hf_hub_download(
            repo_id="nielsr/audio-spectogram-transformer-checkpoint", filename="sample_audio.flac", repo_type="dataset"
        )

    # Need to specify the username on the endpoint `hub-ci`, otherwise we get
    # `fatal: could not read Username for 'https://hub-ci.huggingface.co': Success`
    # But this repo. is never used in a test decorated by `is_staging_test`.
    if not _run_staging:
        if not os.path.isdir("tiny-random-custom-architecture"):
            snapshot_download(
                "hf-internal-testing/tiny-random-custom-architecture",
                local_dir="tiny-random-custom-architecture",
            )

        # For `tests/test_tokenization_mistral_common.py:TestMistralCommonBackend`, which eventually calls
        # `mistral_common.tokens.tokenizers.utils.download_tokenizer_from_hf_hub` which (probably) doesn't have the cache.
        if is_mistral_common_available():
            from mistral_common.tokens.tokenizers.mistral import MistralTokenizer

            from transformers import AutoTokenizer
            from transformers.tokenization_mistral_common import MistralCommonBackend

            repo_id = "hf-internal-testing/namespace-mistralai-repo_name-Mistral-Small-3.1-24B-Instruct-2503"
            AutoTokenizer.from_pretrained(repo_id, tokenizer_type="mistral")
            MistralCommonBackend.from_pretrained(repo_id)
            MistralTokenizer.from_hf_hub(repo_id)

            repo_id = "mistralai/Voxtral-Mini-3B-2507"
            AutoTokenizer.from_pretrained(repo_id)
            MistralTokenizer.from_hf_hub(repo_id)

    # Download files from URLs to local directory
    for url in URLS_FOR_TESTING_DATA:
        filename = url_to_local_path(url, return_url_if_not_found=False)

        # Skip if file already exists
        if os.path.exists(filename):
            print(f"File already exists: {filename}")
            continue

        print(f"Downloading {filename}...")
        try:
            response = requests.get(url, stream=True)
            response.raise_for_status()

            with open(filename, "wb") as f:
                f.writelines(response.iter_content(chunk_size=8192))
            print(f"Successfully downloaded: {filename}")
        except requests.exceptions.RequestException as e:
            print(f"Error downloading {filename}: {e}")