| { | |
| "_name_or_path": "magi", | |
| "architectures": [ | |
| "MagiModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_magi.MagiConfig", | |
| "AutoModel": "modelling_magi.MagiModel" | |
| }, | |
| "crop_embedding_image_preprocessing_config": { | |
| "_processor_class": null, | |
| "do_normalize": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "ViTImageProcessor", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "height": 224, | |
| "width": 224 | |
| } | |
| }, | |
| "crop_embedding_model_config": { | |
| "_name_or_path": "facebook/vit-mae-base", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "ViTMAEForPreTraining" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_hidden_size": 512, | |
| "decoder_intermediate_size": 2048, | |
| "decoder_num_attention_heads": 16, | |
| "decoder_num_hidden_layers": 8, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 224, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "length_penalty": 1.0, | |
| "mask_ratio": 0.75, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "", | |
| "no_repeat_ngram_size": 0, | |
| "norm_pix_loss": false, | |
| "num_attention_heads": 12, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 16, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "qkv_bias": true, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "float32", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "detection_image_preprocessing_config": { | |
| "_processor_class": null, | |
| "do_normalize": true, | |
| "do_pad": true, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "format": "coco_detection", | |
| "image_mean": [ | |
| 0.485, | |
| 0.456, | |
| 0.406 | |
| ], | |
| "image_processor_type": "ConditionalDetrImageProcessor", | |
| "image_std": [ | |
| 0.229, | |
| 0.224, | |
| 0.225 | |
| ], | |
| "resample": 2, | |
| "rescale_factor": 0.00392156862745098, | |
| "size": { | |
| "longest_edge": 1333, | |
| "shortest_edge": 800 | |
| } | |
| }, | |
| "detection_model_config": { | |
| "_name_or_path": "microsoft/conditional-detr-resnet-50", | |
| "activation_dropout": 0.0, | |
| "activation_function": "relu", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "ConditionalDETRForObjectDetection" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auxiliary_loss": false, | |
| "backbone": "resnet50", | |
| "backbone_config": null, | |
| "bad_words_ids": null, | |
| "bbox_cost": 5, | |
| "bbox_loss_coefficient": 5, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "class_cost": 2, | |
| "cls_loss_coefficient": 2, | |
| "cross_attention_hidden_size": null, | |
| "d_model": 256, | |
| "decoder_attention_heads": 8, | |
| "decoder_ffn_dim": 2048, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 6, | |
| "decoder_start_token_id": null, | |
| "dice_loss_coefficient": 1, | |
| "dilation": false, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dropout": 0.1, | |
| "early_stopping": false, | |
| "encoder_attention_heads": 8, | |
| "encoder_ffn_dim": 2048, | |
| "encoder_layerdrop": 0.0, | |
| "encoder_layers": 6, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "focal_alpha": 0.25, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "giou_cost": 2, | |
| "giou_loss_coefficient": 2, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "init_std": 0.02, | |
| "init_xavier_std": 1.0, | |
| "is_decoder": false, | |
| "is_encoder_decoder": true, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2 | |
| }, | |
| "length_penalty": 1.0, | |
| "mask_loss_coefficient": 1, | |
| "max_length": 20, | |
| "max_position_embeddings": 1024, | |
| "min_length": 0, | |
| "model_type": "", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 6, | |
| "num_queries": 305, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "position_embedding_type": "sine", | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "scale_embedding": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "float32", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_pretrained_backbone": true, | |
| "use_timm_backbone": true | |
| }, | |
| "disable_crop_embeddings": false, | |
| "disable_detections": false, | |
| "disable_ocr": false, | |
| "model_type": "magi", | |
| "ocr_model_config": { | |
| "_name_or_path": "/work/rs/logs/manga_ocr/nt8rn2ul/", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "VisionEncoderDecoderModel" | |
| ], | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder": { | |
| "_name_or_path": "", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu", | |
| "add_cross_attention": true, | |
| "architectures": null, | |
| "attention_dropout": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 0, | |
| "chunk_size_feed_forward": 0, | |
| "classifier_dropout": 0.0, | |
| "cross_attention_hidden_size": 768, | |
| "d_model": 1024, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 4096, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 12, | |
| "decoder_start_token_id": 2, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dropout": 0.1, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 2, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "init_std": 0.02, | |
| "is_decoder": true, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layernorm_embedding": true, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 512, | |
| "min_length": 0, | |
| "model_type": "trocr", | |
| "no_repeat_ngram_size": 0, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 1, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "scale_embedding": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_cache": false, | |
| "use_learned_position_embeddings": true, | |
| "vocab_size": 50265 | |
| }, | |
| "decoder_start_token_id": 0, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": true, | |
| "encoder": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": null, | |
| "attention_probs_dropout_prob": 0.0, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "encoder_stride": 16, | |
| "eos_token_id": null, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "image_size": 384, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "min_length": 0, | |
| "model_type": "vit", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 12, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_channels": 3, | |
| "num_hidden_layers": 12, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": null, | |
| "patch_size": 16, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "qkv_bias": false, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": null, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false | |
| }, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eos_token_id": 2, | |
| "exponential_decay_length_penalty": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "is_decoder": false, | |
| "is_encoder_decoder": true, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "length_penalty": 2.0, | |
| "max_length": 300, | |
| "min_length": 0, | |
| "model_type": "vision-encoder-decoder", | |
| "no_repeat_ngram_size": 3, | |
| "num_beam_groups": 1, | |
| "num_beams": 4, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 1, | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "sep_token_id": null, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torch_dtype": "float32", | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "vocab_size": 50265 | |
| }, | |
| "ocr_pretrained_processor_path": "microsoft/trocr-base-printed", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.34.0.dev0" | |
| } | |