diff --git a/docs/source/en/tasks/semantic_segmentation.mdx b/docs/source/en/tasks/semantic_segmentation.mdx index c288449552..3d1b5ef453 100644 --- a/docs/source/en/tasks/semantic_segmentation.mdx +++ b/docs/source/en/tasks/semantic_segmentation.mdx @@ -67,9 +67,9 @@ You'll also want to create a dictionary that maps a label id to a label class wh >>> import json >>> from huggingface_hub import cached_download, hf_hub_url ->>> repo_id = "datasets/huggingface/label-files" +>>> repo_id = "huggingface/label-files" >>> filename = "ade20k-id2label.json" ->>> id2label = json.load(open(cached_download(hf_hub_url(repo_id, filename)), "r")) +>>> id2label = json.load(open(cached_download(hf_hub_url(repo_id, filename, repo_type="dataset")), "r")) >>> id2label = {int(k): v for k, v in id2label.items()} >>> label2id = {v: k for k, v in id2label.items()} >>> num_labels = len(id2label) diff --git a/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py b/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py index c42dc2a41c..bf80991357 100644 --- a/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py +++ b/examples/pytorch/semantic-segmentation/run_semantic_segmentation.py @@ -327,12 +327,12 @@ def main(): # Prepare label mappings. # We'll include these in the model's config to get human readable labels in the Inference API. if data_args.dataset_name == "scene_parse_150": - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "ade20k-id2label.json" else: - repo_id = f"datasets/{data_args.dataset_name}" + repo_id = data_args.dataset_name filename = "id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} label2id = {v: str(k) for k, v in id2label.items()} diff --git a/examples/pytorch/semantic-segmentation/run_semantic_segmentation_no_trainer.py b/examples/pytorch/semantic-segmentation/run_semantic_segmentation_no_trainer.py index cfc32a93c4..8eb1843487 100644 --- a/examples/pytorch/semantic-segmentation/run_semantic_segmentation_no_trainer.py +++ b/examples/pytorch/semantic-segmentation/run_semantic_segmentation_no_trainer.py @@ -387,12 +387,12 @@ def main(): # Prepare label mappings. # We'll include these in the model's config to get human readable labels in the Inference API. if args.dataset_name == "scene_parse_150": - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "ade20k-id2label.json" else: - repo_id = f"datasets/{args.dataset_name}" + repo_id = args.dataset_name filename = "id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/beit/convert_beit_unilm_to_pytorch.py b/src/transformers/models/beit/convert_beit_unilm_to_pytorch.py index 90b174d5d4..b9287c05bd 100644 --- a/src/transformers/models/beit/convert_beit_unilm_to_pytorch.py +++ b/src/transformers/models/beit/convert_beit_unilm_to_pytorch.py @@ -176,7 +176,7 @@ def convert_beit_checkpoint(checkpoint_url, pytorch_dump_folder_path): config = BeitConfig() has_lm_head = False is_semantic = False - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" # set config parameters based on URL if checkpoint_url[-9:-4] == "pt22k": # masked image modeling @@ -188,7 +188,7 @@ def convert_beit_checkpoint(checkpoint_url, pytorch_dump_folder_path): config.use_relative_position_bias = True config.num_labels = 21841 filename = "imagenet-22k-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} # this dataset contains 21843 labels but the model only has 21841 # we delete the classes as mentioned in https://github.com/google-research/big_transfer/issues/18 @@ -201,7 +201,7 @@ def convert_beit_checkpoint(checkpoint_url, pytorch_dump_folder_path): config.use_relative_position_bias = True config.num_labels = 1000 filename = "imagenet-1k-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} @@ -214,7 +214,7 @@ def convert_beit_checkpoint(checkpoint_url, pytorch_dump_folder_path): config.use_relative_position_bias = True config.num_labels = 150 filename = "ade20k-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/conditional_detr/convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/conditional_detr/convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.py index 904530c44c..a4e28cbb55 100644 --- a/src/transformers/models/conditional_detr/convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/conditional_detr/convert_conditional_detr_original_pytorch_checkpoint_to_pytorch.py @@ -237,9 +237,9 @@ def convert_conditional_detr_checkpoint(model_name, pytorch_dump_folder_path): config.num_labels = 250 else: config.num_labels = 91 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "coco-detection-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/convnext/convert_convnext_to_pytorch.py b/src/transformers/models/convnext/convert_convnext_to_pytorch.py index 4d18bfc9b4..e40565c7a6 100644 --- a/src/transformers/models/convnext/convert_convnext_to_pytorch.py +++ b/src/transformers/models/convnext/convert_convnext_to_pytorch.py @@ -62,9 +62,9 @@ def get_convnext_config(checkpoint_url): filename = "imagenet-22k-id2label.json" expected_shape = (1, 21841) - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" config.num_labels = num_labels - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} if "1k" not in checkpoint_url: # this dataset contains 21843 labels but the model only has 21841 diff --git a/src/transformers/models/cvt/convert_cvt_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/cvt/convert_cvt_original_pytorch_checkpoint_to_pytorch.py index a33487c9e6..72a8be4bef 100644 --- a/src/transformers/models/cvt/convert_cvt_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/cvt/convert_cvt_original_pytorch_checkpoint_to_pytorch.py @@ -282,9 +282,9 @@ def convert_cvt_checkpoint(cvt_model, image_size, cvt_file_name, pytorch_dump_fo img_labels_file = "imagenet-1k-id2label.json" num_labels = 1000 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" num_labels = num_labels - id2label = json.load(open(cached_download(hf_hub_url(repo_id, img_labels_file)), "r")) + id2label = json.load(open(cached_download(hf_hub_url(repo_id, img_labels_file, repo_type="dataset")), "r")) id2label = {int(k): v for k, v in id2label.items()} id2label = id2label diff --git a/src/transformers/models/data2vec/convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/data2vec/convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py index b375167c8d..7777e85927 100755 --- a/src/transformers/models/data2vec/convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/data2vec/convert_data2vec_vision_original_pytorch_checkpoint_to_pytorch.py @@ -282,9 +282,9 @@ def main(): config.use_mean_pooling = True config.num_labels = 1000 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "imagenet-1k-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py b/src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py index 30726c5e97..8e4461d515 100644 --- a/src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py +++ b/src/transformers/models/deformable_detr/convert_deformable_detr_to_pytorch.py @@ -108,9 +108,9 @@ def convert_deformable_detr_checkpoint( config.two_stage = two_stage # set labels config.num_labels = 91 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "coco-detection-id2label.json" - id2label = json.load(open(cached_download(hf_hub_url(repo_id, filename)), "r")) + id2label = json.load(open(cached_download(hf_hub_url(repo_id, filename, repo_type="dataset")), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/deit/convert_deit_timm_to_pytorch.py b/src/transformers/models/deit/convert_deit_timm_to_pytorch.py index a9225c819b..8a8a394c3f 100644 --- a/src/transformers/models/deit/convert_deit_timm_to_pytorch.py +++ b/src/transformers/models/deit/convert_deit_timm_to_pytorch.py @@ -140,9 +140,9 @@ def convert_deit_checkpoint(deit_name, pytorch_dump_folder_path): base_model = False # dataset (fine-tuned on ImageNet 2012), patch_size and image_size config.num_labels = 1000 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "imagenet-1k-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/detr/convert_detr_original_pytorch_checkpoint_to_pytorch.py b/src/transformers/models/detr/convert_detr_original_pytorch_checkpoint_to_pytorch.py index feb9d98eb7..abb7ed72a8 100644 --- a/src/transformers/models/detr/convert_detr_original_pytorch_checkpoint_to_pytorch.py +++ b/src/transformers/models/detr/convert_detr_original_pytorch_checkpoint_to_pytorch.py @@ -194,9 +194,9 @@ def convert_detr_checkpoint(model_name, pytorch_dump_folder_path): config.num_labels = 250 else: config.num_labels = 91 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "coco-detection-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/dit/convert_dit_unilm_to_pytorch.py b/src/transformers/models/dit/convert_dit_unilm_to_pytorch.py index e005946db6..07c1a3094c 100644 --- a/src/transformers/models/dit/convert_dit_unilm_to_pytorch.py +++ b/src/transformers/models/dit/convert_dit_unilm_to_pytorch.py @@ -149,9 +149,9 @@ def convert_dit_checkpoint(checkpoint_url, pytorch_dump_folder_path, push_to_hub # labels if "rvlcdip" in checkpoint_url: config.num_labels = 16 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "rvlcdip-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/dpt/convert_dpt_to_pytorch.py b/src/transformers/models/dpt/convert_dpt_to_pytorch.py index 0050f5e0a8..dc26d017d7 100644 --- a/src/transformers/models/dpt/convert_dpt_to_pytorch.py +++ b/src/transformers/models/dpt/convert_dpt_to_pytorch.py @@ -48,9 +48,9 @@ def get_dpt_config(checkpoint_url): config.use_batch_norm_in_fusion_residual = True config.num_labels = 150 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "ade20k-id2label.json" - id2label = json.load(open(cached_download(hf_hub_url(repo_id, filename)), "r")) + id2label = json.load(open(cached_download(hf_hub_url(repo_id, filename, repo_type="dataset")), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/levit/convert_levit_timm_to_pytorch.py b/src/transformers/models/levit/convert_levit_timm_to_pytorch.py index d9449aad7a..a3b59ee876 100644 --- a/src/transformers/models/levit/convert_levit_timm_to_pytorch.py +++ b/src/transformers/models/levit/convert_levit_timm_to_pytorch.py @@ -85,9 +85,9 @@ def convert_weights_and_push(save_directory: Path, model_name: str = None, push_ num_labels = 1000 expected_shape = (1, num_labels) - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" num_labels = num_labels - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} id2label = id2label diff --git a/src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py b/src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py index 7f3e07f7b5..bc61f8822e 100644 --- a/src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py +++ b/src/transformers/models/mobilevit/convert_mlcvnets_to_pytorch.py @@ -62,8 +62,8 @@ def get_mobilevit_config(mobilevit_name): config.num_labels = 1000 filename = "imagenet-1k-id2label.json" - repo_id = "datasets/huggingface/label-files" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + repo_id = "huggingface/label-files" + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py b/src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py index d1af1f3667..d1a4fd14e5 100644 --- a/src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py +++ b/src/transformers/models/perceiver/convert_perceiver_haiku_to_pytorch.py @@ -300,7 +300,7 @@ def convert_perceiver_checkpoint(pickle_file, pytorch_dump_folder_path, architec # load HuggingFace model config = PerceiverConfig() subsampling = None - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" if architecture == "MLM": config.qk_channels = 8 * 32 config.v_channels = 1280 @@ -318,7 +318,7 @@ def convert_perceiver_checkpoint(pickle_file, pytorch_dump_folder_path, architec # set labels config.num_labels = 1000 filename = "imagenet-1k-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} @@ -367,7 +367,7 @@ def convert_perceiver_checkpoint(pickle_file, pytorch_dump_folder_path, architec model = PerceiverForMultimodalAutoencoding(config) # set labels filename = "kinetics700-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py b/src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py index 6bb6ec2510..4ab0d2bfb3 100644 --- a/src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py +++ b/src/transformers/models/poolformer/convert_poolformer_original_to_pytorch.py @@ -99,14 +99,14 @@ def convert_poolformer_checkpoint(model_name, checkpoint_path, pytorch_dump_fold config = PoolFormerConfig() # set attributes based on model_name - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" size = model_name[-3:] config.num_labels = 1000 filename = "imagenet-1k-id2label.json" expected_shape = (1, 1000) # set config attributes - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/regnet/convert_regnet_seer_10b_to_pytorch.py b/src/transformers/models/regnet/convert_regnet_seer_10b_to_pytorch.py index a43967d009..4a73b9623f 100644 --- a/src/transformers/models/regnet/convert_regnet_seer_10b_to_pytorch.py +++ b/src/transformers/models/regnet/convert_regnet_seer_10b_to_pytorch.py @@ -163,9 +163,9 @@ def convert_weights_and_push(save_directory: Path, model_name: str = None, push_ filename = "imagenet-1k-id2label.json" num_labels = 1000 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" num_labels = num_labels - id2label = json.load(open(cached_download(hf_hub_url(repo_id, filename)), "r")) + id2label = json.load(open(cached_download(hf_hub_url(repo_id, filename, repo_type="dataset")), "r")) id2label = {int(k): v for k, v in id2label.items()} id2label = id2label diff --git a/src/transformers/models/regnet/convert_regnet_to_pytorch.py b/src/transformers/models/regnet/convert_regnet_to_pytorch.py index 9bb0ba0f05..acb74dc89d 100644 --- a/src/transformers/models/regnet/convert_regnet_to_pytorch.py +++ b/src/transformers/models/regnet/convert_regnet_to_pytorch.py @@ -224,9 +224,9 @@ def convert_weights_and_push(save_directory: Path, model_name: str = None, push_ num_labels = 1000 expected_shape = (1, num_labels) - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" num_labels = num_labels - id2label = json.load(open(cached_download(hf_hub_url(repo_id, filename)), "r")) + id2label = json.load(open(cached_download(hf_hub_url(repo_id, filename, repo_type="dataset")), "r")) id2label = {int(k): v for k, v in id2label.items()} id2label = id2label diff --git a/src/transformers/models/resnet/convert_resnet_to_pytorch.py b/src/transformers/models/resnet/convert_resnet_to_pytorch.py index 55a865ed59..ef3d564185 100644 --- a/src/transformers/models/resnet/convert_resnet_to_pytorch.py +++ b/src/transformers/models/resnet/convert_resnet_to_pytorch.py @@ -128,9 +128,9 @@ def convert_weights_and_push(save_directory: Path, model_name: str = None, push_ num_labels = 1000 expected_shape = (1, num_labels) - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" num_labels = num_labels - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} id2label = id2label diff --git a/src/transformers/models/segformer/convert_segformer_original_to_pytorch.py b/src/transformers/models/segformer/convert_segformer_original_to_pytorch.py index da0ca7b3cc..00dddc9974 100644 --- a/src/transformers/models/segformer/convert_segformer_original_to_pytorch.py +++ b/src/transformers/models/segformer/convert_segformer_original_to_pytorch.py @@ -128,7 +128,7 @@ def convert_segformer_checkpoint(model_name, checkpoint_path, pytorch_dump_folde encoder_only = False # set attributes based on model_name - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" if "segformer" in model_name: size = model_name[len("segformer.") : len("segformer.") + 2] if "ade" in model_name: @@ -151,7 +151,7 @@ def convert_segformer_checkpoint(model_name, checkpoint_path, pytorch_dump_folde raise ValueError(f"Model {model_name} not supported") # set config attributes - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/swin/convert_swin_timm_to_pytorch.py b/src/transformers/models/swin/convert_swin_timm_to_pytorch.py index 0d09d27fa2..860fdd1b54 100644 --- a/src/transformers/models/swin/convert_swin_timm_to_pytorch.py +++ b/src/transformers/models/swin/convert_swin_timm_to_pytorch.py @@ -39,9 +39,9 @@ def get_swin_config(swin_name): num_classes = 21841 else: num_classes = 1000 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "imagenet-1k-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py b/src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py index 148793e304..7af3bfb86c 100644 --- a/src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py +++ b/src/transformers/models/swinv2/convert_swinv2_timm_to_pytorch.py @@ -63,18 +63,18 @@ def get_swinv2_config(swinv2_name): if ("22k" in swinv2_name) and ("to" not in swinv2_name): num_classes = 21841 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "imagenet-22k-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} else: num_classes = 1000 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "imagenet-1k-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/van/convert_van_to_pytorch.py b/src/transformers/models/van/convert_van_to_pytorch.py index e2c0c95e64..ded3c3500d 100644 --- a/src/transformers/models/van/convert_van_to_pytorch.py +++ b/src/transformers/models/van/convert_van_to_pytorch.py @@ -168,9 +168,9 @@ def convert_weights_and_push(save_directory: Path, model_name: str = None, push_ filename = "imagenet-1k-id2label.json" num_labels = 1000 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" num_labels = num_labels - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} id2label = id2label diff --git a/src/transformers/models/videomae/convert_videomae_to_pytorch.py b/src/transformers/models/videomae/convert_videomae_to_pytorch.py index 60e5ae8f5f..2f4ce5d447 100644 --- a/src/transformers/models/videomae/convert_videomae_to_pytorch.py +++ b/src/transformers/models/videomae/convert_videomae_to_pytorch.py @@ -47,7 +47,7 @@ def get_videomae_config(model_name): config.use_mean_pooling = False if "finetuned" in model_name: - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" if "kinetics" in model_name: config.num_labels = 400 filename = "kinetics400-id2label.json" @@ -56,7 +56,7 @@ def get_videomae_config(model_name): filename = "something-something-v2-id2label.json" else: raise ValueError("Model name should either contain 'kinetics' or 'ssv2' in case it's fine-tuned.") - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} @@ -145,7 +145,9 @@ def convert_state_dict(orig_state_dict, config): # We will verify our results on a video of eating spaghetti # Frame indices used: [164 168 172 176 181 185 189 193 198 202 206 210 215 219 223 227] def prepare_video(): - file = hf_hub_download(repo_id="datasets/hf-internal-testing/spaghetti-video", filename="eating_spaghetti.npy") + file = hf_hub_download( + repo_id="hf-internal-testing/spaghetti-video", filename="eating_spaghetti.npy", repo_type="dataset" + ) video = np.load(file) return list(video) diff --git a/src/transformers/models/vilt/convert_vilt_original_to_pytorch.py b/src/transformers/models/vilt/convert_vilt_original_to_pytorch.py index 3a186e1d2d..5e737f784c 100644 --- a/src/transformers/models/vilt/convert_vilt_original_to_pytorch.py +++ b/src/transformers/models/vilt/convert_vilt_original_to_pytorch.py @@ -180,9 +180,9 @@ def convert_vilt_checkpoint(checkpoint_url, pytorch_dump_folder_path): if "vqa" in checkpoint_url: vqa_model = True config.num_labels = 3129 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "vqa2-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/vit/convert_dino_to_pytorch.py b/src/transformers/models/vit/convert_dino_to_pytorch.py index 8922684594..1a8ba21a65 100644 --- a/src/transformers/models/vit/convert_dino_to_pytorch.py +++ b/src/transformers/models/vit/convert_dino_to_pytorch.py @@ -142,9 +142,9 @@ def convert_vit_checkpoint(model_name, pytorch_dump_folder_path, base_model=True # set labels if required if not base_model: config.num_labels = 1000 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "imagenet-1k-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/vit/convert_vit_timm_to_pytorch.py b/src/transformers/models/vit/convert_vit_timm_to_pytorch.py index 30495bd0f1..bc1f7f72dd 100644 --- a/src/transformers/models/vit/convert_vit_timm_to_pytorch.py +++ b/src/transformers/models/vit/convert_vit_timm_to_pytorch.py @@ -147,9 +147,9 @@ def convert_vit_checkpoint(vit_name, pytorch_dump_folder_path): config.image_size = int(vit_name[-9:-6]) else: config.num_labels = 1000 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "imagenet-1k-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/src/transformers/models/x_clip/convert_x_clip_original_pytorch_to_hf.py b/src/transformers/models/x_clip/convert_x_clip_original_pytorch_to_hf.py index 2f5364f440..8210b3f709 100644 --- a/src/transformers/models/x_clip/convert_x_clip_original_pytorch_to_hf.py +++ b/src/transformers/models/x_clip/convert_x_clip_original_pytorch_to_hf.py @@ -207,8 +207,9 @@ def prepare_video(num_frames): elif num_frames == 32: filename = "eating_spaghetti_32_frames.npy" file = hf_hub_download( - repo_id="datasets/hf-internal-testing/spaghetti-video", + repo_id="hf-internal-testing/spaghetti-video", filename=filename, + repo_type="dataset", ) video = np.load(file) return list(video) diff --git a/src/transformers/models/yolos/convert_yolos_to_pytorch.py b/src/transformers/models/yolos/convert_yolos_to_pytorch.py index 7f4161a632..be840151a1 100644 --- a/src/transformers/models/yolos/convert_yolos_to_pytorch.py +++ b/src/transformers/models/yolos/convert_yolos_to_pytorch.py @@ -57,9 +57,9 @@ def get_yolos_config(yolos_name): config.image_size = [800, 1344] config.num_labels = 91 - repo_id = "datasets/huggingface/label-files" + repo_id = "huggingface/label-files" filename = "coco-detection-id2label.json" - id2label = json.load(open(hf_hub_download(repo_id, filename), "r")) + id2label = json.load(open(hf_hub_download(repo_id, filename, repo_type="dataset"), "r")) id2label = {int(k): v for k, v in id2label.items()} config.id2label = id2label config.label2id = {v: k for k, v in id2label.items()} diff --git a/tests/models/videomae/test_modeling_videomae.py b/tests/models/videomae/test_modeling_videomae.py index adce62021c..bc665410b6 100644 --- a/tests/models/videomae/test_modeling_videomae.py +++ b/tests/models/videomae/test_modeling_videomae.py @@ -342,7 +342,9 @@ class VideoMAEModelTest(ModelTesterMixin, unittest.TestCase): # We will verify our results on a video of eating spaghetti # Frame indices used: [164 168 172 176 181 185 189 193 198 202 206 210 215 219 223 227] def prepare_video(): - file = hf_hub_download(repo_id="datasets/hf-internal-testing/spaghetti-video", filename="eating_spaghetti.npy") + file = hf_hub_download( + repo_id="hf-internal-testing/spaghetti-video", filename="eating_spaghetti.npy", repo_type="dataset" + ) video = np.load(file) return list(video) diff --git a/tests/models/x_clip/test_modeling_x_clip.py b/tests/models/x_clip/test_modeling_x_clip.py index 62c8e9992b..0a70fdcb44 100644 --- a/tests/models/x_clip/test_modeling_x_clip.py +++ b/tests/models/x_clip/test_modeling_x_clip.py @@ -633,7 +633,7 @@ class XCLIPModelTest(ModelTesterMixin, unittest.TestCase): # We will verify our results on a spaghetti video def prepare_video(): file = hf_hub_download( - repo_id="datasets/hf-internal-testing/spaghetti-video", filename="eating_spaghetti_8_frames.npy" + repo_id="hf-internal-testing/spaghetti-video", filename="eating_spaghetti_8_frames.npy", repo_type="dataset" ) video = np.load(file) return list(video)