| { |
| "model_type": "indic_ocr", |
| "stages": { |
| "layout": { |
| "name": "IndicDocLayout", |
| "config": "weights/layout/config.json", |
| "weights": "weights/layout/model.safetensors" |
| }, |
| "ocr": { |
| "name": "IndicBlockOCR", |
| "config": "weights/ocr/config.json", |
| "weights": "weights/ocr/model.safetensors" |
| } |
| }, |
| "layout_config": { |
| "activation_dropout": 0.0, |
| "activation_function": "silu", |
| "anchor_image_size": null, |
| "architectures": [ |
| "PPDocLayoutV3Trainable" |
| ], |
| "attention_dropout": 0.0, |
| "auxiliary_loss": true, |
| "backbone": null, |
| "backbone_config": { |
| "arch": "L", |
| "depths": [ |
| 3, |
| 4, |
| 6, |
| 3 |
| ], |
| "dtype": "float32", |
| "embedding_size": 64, |
| "freeze_at": 0, |
| "freeze_norm": true, |
| "freeze_stem_only": true, |
| "hidden_act": "relu", |
| "hidden_sizes": [ |
| 256, |
| 512, |
| 1024, |
| 2048 |
| ], |
| "initializer_range": 0.02, |
| "lr_mult_list": [ |
| 0, |
| 0.05, |
| 0.05, |
| 0.05, |
| 0.05 |
| ], |
| "model_type": "hgnet_v2", |
| "num_channels": 3, |
| "out_features": [ |
| "stage1", |
| "stage2", |
| "stage3", |
| "stage4" |
| ], |
| "out_indices": [ |
| 1, |
| 2, |
| 3, |
| 4 |
| ], |
| "return_idx": [ |
| 0, |
| 1, |
| 2, |
| 3 |
| ], |
| "stage_downsample": [ |
| false, |
| true, |
| true, |
| true |
| ], |
| "stage_downsample_strides": [ |
| 2, |
| 2, |
| 2, |
| 2 |
| ], |
| "stage_in_channels": [ |
| 48, |
| 128, |
| 512, |
| 1024 |
| ], |
| "stage_kernel_size": [ |
| 3, |
| 3, |
| 5, |
| 5 |
| ], |
| "stage_light_block": [ |
| false, |
| false, |
| true, |
| true |
| ], |
| "stage_mid_channels": [ |
| 48, |
| 96, |
| 192, |
| 384 |
| ], |
| "stage_names": [ |
| "stem", |
| "stage1", |
| "stage2", |
| "stage3", |
| "stage4" |
| ], |
| "stage_num_blocks": [ |
| 1, |
| 1, |
| 3, |
| 1 |
| ], |
| "stage_numb_of_layers": [ |
| 6, |
| 6, |
| 6, |
| 6 |
| ], |
| "stage_out_channels": [ |
| 128, |
| 512, |
| 1024, |
| 2048 |
| ], |
| "stem_channels": [ |
| 3, |
| 32, |
| 48 |
| ], |
| "stem_strides": [ |
| 2, |
| 1, |
| 1, |
| 2, |
| 1 |
| ], |
| "use_learnable_affine_block": false |
| }, |
| "batch_norm_eps": 1e-05, |
| "box_noise_scale": 1.0, |
| "d_model": 256, |
| "decoder_activation_function": "relu", |
| "decoder_attention_heads": 8, |
| "decoder_ffn_dim": 1024, |
| "decoder_in_channels": [ |
| 256, |
| 256, |
| 256 |
| ], |
| "decoder_layers": 6, |
| "decoder_n_points": 4, |
| "disable_custom_kernels": true, |
| "dropout": 0.0, |
| "dtype": "float32", |
| "encode_proj_layers": [ |
| 2 |
| ], |
| "encoder_activation_function": "gelu", |
| "encoder_attention_heads": 8, |
| "encoder_ffn_dim": 1024, |
| "encoder_hidden_dim": 256, |
| "encoder_in_channels": [ |
| 512, |
| 1024, |
| 2048 |
| ], |
| "encoder_layers": 1, |
| "eos_coefficient": 0.0001, |
| "eval_size": null, |
| "feat_strides": [ |
| 8, |
| 16, |
| 32 |
| ], |
| "feature_strides": [ |
| 8, |
| 16, |
| 32 |
| ], |
| "focal_loss_alpha": 0.25, |
| "focal_loss_gamma": 2.0, |
| "freeze_backbone_batch_norms": true, |
| "global_pointer_head_size": 64, |
| "gp_dropout_value": 0.1, |
| "hidden_expansion": 1.0, |
| "id2label": { |
| "0": "Question", |
| "1": "Paragraph", |
| "2": "Answer", |
| "3": "List", |
| "4": "Title", |
| "5": "Section-title", |
| "6": "Equation", |
| "7": "Table", |
| "8": "Diagram", |
| "9": "Image", |
| "10": "MCQ", |
| "11": "Infobox", |
| "12": "Sub-section-title", |
| "13": "Expression", |
| "14": "Image-caption", |
| "15": "Placeholder-text", |
| "16": "Chart", |
| "17": "Solved-example", |
| "18": "Footnote", |
| "19": "Table-caption", |
| "20": "Sub-sub-section-title", |
| "21": "Footer", |
| "22": "Header", |
| "23": "Code", |
| "24": "Page-number", |
| "25": "Chapter-title", |
| "26": "Chapter-end-section", |
| "27": "Folio", |
| "28": "Reference", |
| "29": "Table-of-contents", |
| "30": "Index", |
| "31": "Advertisement", |
| "32": "Author", |
| "33": "Dateline", |
| "34": "Contact-info", |
| "35": "Website-link", |
| "36": "Flag" |
| }, |
| "initializer_bias_prior_prob": null, |
| "initializer_range": 0.01, |
| "is_encoder_decoder": true, |
| "label2id": { |
| "Advertisement": 31, |
| "Answer": 2, |
| "Author": 32, |
| "Chapter-end-section": 26, |
| "Chapter-title": 25, |
| "Chart": 16, |
| "Code": 23, |
| "Contact-info": 34, |
| "Dateline": 33, |
| "Diagram": 8, |
| "Equation": 6, |
| "Expression": 13, |
| "Flag": 36, |
| "Folio": 27, |
| "Footer": 21, |
| "Footnote": 18, |
| "Header": 22, |
| "Image": 9, |
| "Image-caption": 14, |
| "Index": 30, |
| "Infobox": 11, |
| "List": 3, |
| "MCQ": 10, |
| "Page-number": 24, |
| "Paragraph": 1, |
| "Placeholder-text": 15, |
| "Question": 0, |
| "Reference": 28, |
| "Section-title": 5, |
| "Solved-example": 17, |
| "Sub-section-title": 12, |
| "Sub-sub-section-title": 20, |
| "Table": 7, |
| "Table-caption": 19, |
| "Table-of-contents": 29, |
| "Title": 4, |
| "Website-link": 35 |
| }, |
| "label_noise_ratio": 0.5, |
| "lambda_order": 5.0, |
| "layer_norm_eps": 1e-05, |
| "learn_initial_query": false, |
| "loss_type": "RTDetrForObjectDetection", |
| "mask_enhanced": true, |
| "mask_feature_channels": [ |
| 64, |
| 64 |
| ], |
| "matcher_alpha": 0.25, |
| "matcher_bbox_cost": 5.0, |
| "matcher_class_cost": 2.0, |
| "matcher_gamma": 2.0, |
| "matcher_giou_cost": 2.0, |
| "model_type": "pp_doclayout_v3", |
| "normalize_before": false, |
| "num_denoising": 0, |
| "num_feature_levels": 3, |
| "num_prototypes": 32, |
| "num_queries": 300, |
| "positional_encoding_temperature": 10000, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.8.1", |
| "use_cache": false, |
| "use_focal_loss": true, |
| "weight_loss_bbox": 5.0, |
| "weight_loss_giou": 2.0, |
| "weight_loss_vfl": 1.0, |
| "x4_feat_dim": 128 |
| }, |
| "ocr_config": { |
| "architectures": [ |
| "Qwen3_5ForConditionalGeneration" |
| ], |
| "chunk_size_feed_forward": 0, |
| "dtype": "bfloat16", |
| "eos_token_id": 262146, |
| "generation_config": { |
| "_from_model_config": true, |
| "eos_token_id": 262146, |
| "transformers_version": "5.6.2", |
| "use_cache": true |
| }, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "image_token_id": 262155, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "model_type": "indic_ocr", |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "problem_type": null, |
| "return_dict": true, |
| "text_config": { |
| "_name_or_path": "", |
| "architectures": null, |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "attn_output_gate": true, |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "dtype": "bfloat16", |
| "eos_token_id": 262146, |
| "full_attention_interval": 4, |
| "head_dim": 256, |
| "hidden_act": "silu", |
| "hidden_size": 1024, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3584, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layer_types": [ |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention", |
| "linear_attention", |
| "linear_attention", |
| "linear_attention", |
| "full_attention" |
| ], |
| "linear_conv_kernel_dim": 4, |
| "linear_key_head_dim": 128, |
| "linear_num_key_heads": 16, |
| "linear_num_value_heads": 16, |
| "linear_value_head_dim": 128, |
| "mamba_ssm_dtype": "float32", |
| "max_position_embeddings": 262144, |
| "mlp_only_layers": [], |
| "model_type": "qwen3_5_text", |
| "mtp_num_hidden_layers": 1, |
| "mtp_use_dedicated_embeddings": false, |
| "num_attention_heads": 8, |
| "num_hidden_layers": 24, |
| "num_key_value_heads": 2, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "pad_token_id": 262144, |
| "partial_rotary_factor": 0.25, |
| "problem_type": null, |
| "return_dict": true, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "mrope_interleaved": true, |
| "mrope_section": [ |
| 11, |
| 11, |
| 10 |
| ], |
| "partial_rotary_factor": 0.25, |
| "rope_theta": 10000000, |
| "type": "default" |
| }, |
| "tie_word_embeddings": true, |
| "use_cache": false, |
| "vocab_size": 262157 |
| }, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.6.2", |
| "use_cache": false, |
| "video_token_id": 262156, |
| "vision_config": { |
| "_name_or_path": "", |
| "architectures": null, |
| "chunk_size_feed_forward": 0, |
| "deepstack_visual_indexes": [], |
| "depth": 12, |
| "dtype": "bfloat16", |
| "hidden_act": "gelu_pytorch_tanh", |
| "hidden_size": 768, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "in_channels": 3, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "model_type": "qwen3_5_vision", |
| "num_heads": 12, |
| "num_position_embeddings": 2304, |
| "out_hidden_size": 1024, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "patch_size": 16, |
| "problem_type": null, |
| "return_dict": true, |
| "spatial_merge_size": 2, |
| "temporal_patch_size": 2 |
| }, |
| "vision_end_token_id": 262154, |
| "vision_start_token_id": 262153 |
| }, |
| "ocr_model_path": "weights/ocr", |
| "weight_mapping": { |
| "backbone.embedder.stem1.bn.bias": "layout", |
| "backbone.embedder.stem1.bn.running_mean": "layout", |
| "backbone.embedder.stem1.bn.running_var": "layout", |
| "backbone.embedder.stem1.bn.weight": "layout", |
| "backbone.embedder.stem1.conv.weight": "layout", |
| "backbone.embedder.stem2a.bn.bias": "layout", |
| "backbone.embedder.stem2a.bn.running_mean": "layout", |
| "backbone.embedder.stem2a.bn.running_var": "layout", |
| "backbone.embedder.stem2a.bn.weight": "layout", |
| "backbone.embedder.stem2a.conv.weight": "layout", |
| "backbone.embedder.stem2b.bn.bias": "layout", |
| "backbone.embedder.stem2b.bn.running_mean": "layout", |
| "backbone.embedder.stem2b.bn.running_var": "layout", |
| "backbone.embedder.stem2b.bn.weight": "layout", |
| "backbone.embedder.stem2b.conv.weight": "layout", |
| "backbone.embedder.stem3.bn.bias": "layout", |
| "backbone.embedder.stem3.bn.running_mean": "layout", |
| "backbone.embedder.stem3.bn.running_var": "layout", |
| "backbone.embedder.stem3.bn.weight": "layout", |
| "backbone.embedder.stem3.conv.weight": "layout", |
| "backbone.embedder.stem4.bn.bias": "layout", |
| "backbone.embedder.stem4.bn.running_mean": "layout", |
| "backbone.embedder.stem4.bn.running_var": "layout", |
| "backbone.embedder.stem4.bn.weight": "layout", |
| "backbone.embedder.stem4.conv.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.aggregation.0.bn.bias": "layout", |
| "backbone.encoder.stages.0.blocks.0.aggregation.0.bn.running_mean": "layout", |
| "backbone.encoder.stages.0.blocks.0.aggregation.0.bn.running_var": "layout", |
| "backbone.encoder.stages.0.blocks.0.aggregation.0.bn.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.aggregation.0.conv.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.aggregation.1.bn.bias": "layout", |
| "backbone.encoder.stages.0.blocks.0.aggregation.1.bn.running_mean": "layout", |
| "backbone.encoder.stages.0.blocks.0.aggregation.1.bn.running_var": "layout", |
| "backbone.encoder.stages.0.blocks.0.aggregation.1.bn.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.aggregation.1.conv.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.0.bn.bias": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.0.bn.running_mean": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.0.bn.running_var": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.0.bn.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.0.conv.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.1.bn.bias": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.1.bn.running_mean": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.1.bn.running_var": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.1.bn.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.1.conv.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.2.bn.bias": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.2.bn.running_mean": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.2.bn.running_var": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.2.bn.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.2.conv.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.3.bn.bias": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.3.bn.running_mean": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.3.bn.running_var": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.3.bn.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.3.conv.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.4.bn.bias": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.4.bn.running_mean": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.4.bn.running_var": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.4.bn.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.4.conv.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.5.bn.bias": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.5.bn.running_mean": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.5.bn.running_var": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.5.bn.weight": "layout", |
| "backbone.encoder.stages.0.blocks.0.layers.5.conv.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.aggregation.0.bn.bias": "layout", |
| "backbone.encoder.stages.1.blocks.0.aggregation.0.bn.running_mean": "layout", |
| "backbone.encoder.stages.1.blocks.0.aggregation.0.bn.running_var": "layout", |
| "backbone.encoder.stages.1.blocks.0.aggregation.0.bn.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.aggregation.0.conv.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.aggregation.1.bn.bias": "layout", |
| "backbone.encoder.stages.1.blocks.0.aggregation.1.bn.running_mean": "layout", |
| "backbone.encoder.stages.1.blocks.0.aggregation.1.bn.running_var": "layout", |
| "backbone.encoder.stages.1.blocks.0.aggregation.1.bn.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.aggregation.1.conv.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.0.bn.bias": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.0.bn.running_mean": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.0.bn.running_var": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.0.bn.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.0.conv.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.1.bn.bias": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.1.bn.running_mean": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.1.bn.running_var": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.1.bn.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.1.conv.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.2.bn.bias": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.2.bn.running_mean": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.2.bn.running_var": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.2.bn.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.2.conv.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.3.bn.bias": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.3.bn.running_mean": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.3.bn.running_var": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.3.bn.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.3.conv.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.4.bn.bias": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.4.bn.running_mean": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.4.bn.running_var": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.4.bn.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.4.conv.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.5.bn.bias": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.5.bn.running_mean": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.5.bn.running_var": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.5.bn.weight": "layout", |
| "backbone.encoder.stages.1.blocks.0.layers.5.conv.weight": "layout", |
| "backbone.encoder.stages.1.downsample.bn.bias": "layout", |
| "backbone.encoder.stages.1.downsample.bn.running_mean": "layout", |
| "backbone.encoder.stages.1.downsample.bn.running_var": "layout", |
| "backbone.encoder.stages.1.downsample.bn.weight": "layout", |
| "backbone.encoder.stages.1.downsample.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.aggregation.0.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.aggregation.0.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.aggregation.0.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.aggregation.0.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.aggregation.0.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.aggregation.1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.aggregation.1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.aggregation.1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.aggregation.1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.aggregation.1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.0.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.0.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.0.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.0.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.0.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.0.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.0.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.0.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.0.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.0.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.1.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.1.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.1.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.1.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.1.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.1.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.1.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.1.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.1.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.1.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.2.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.2.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.2.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.2.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.2.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.2.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.2.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.2.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.2.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.2.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.3.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.3.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.3.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.3.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.3.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.3.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.3.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.3.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.3.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.3.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.4.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.4.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.4.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.4.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.4.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.4.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.4.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.4.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.4.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.4.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.5.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.5.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.5.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.5.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.5.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.5.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.5.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.5.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.5.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.0.layers.5.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.aggregation.0.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.aggregation.0.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.aggregation.0.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.aggregation.0.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.aggregation.0.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.aggregation.1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.aggregation.1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.aggregation.1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.aggregation.1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.aggregation.1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.0.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.0.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.0.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.0.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.0.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.0.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.0.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.0.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.0.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.0.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.1.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.1.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.1.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.1.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.1.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.1.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.1.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.1.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.1.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.1.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.2.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.2.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.2.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.2.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.2.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.2.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.2.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.2.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.2.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.2.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.3.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.3.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.3.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.3.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.3.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.3.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.3.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.3.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.3.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.3.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.4.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.4.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.4.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.4.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.4.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.4.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.4.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.4.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.4.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.4.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.5.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.5.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.5.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.5.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.5.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.5.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.5.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.5.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.5.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.1.layers.5.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.aggregation.0.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.aggregation.0.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.aggregation.0.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.aggregation.0.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.aggregation.0.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.aggregation.1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.aggregation.1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.aggregation.1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.aggregation.1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.aggregation.1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.0.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.0.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.0.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.0.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.0.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.0.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.0.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.0.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.0.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.0.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.1.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.1.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.1.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.1.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.1.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.1.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.1.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.1.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.1.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.1.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.2.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.2.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.2.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.2.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.2.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.2.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.2.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.2.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.2.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.2.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.3.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.3.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.3.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.3.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.3.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.3.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.3.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.3.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.3.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.3.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.4.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.4.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.4.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.4.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.4.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.4.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.4.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.4.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.4.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.4.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.5.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.5.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.5.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.5.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.5.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.5.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.5.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.5.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.5.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.2.blocks.2.layers.5.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.2.downsample.bn.bias": "layout", |
| "backbone.encoder.stages.2.downsample.bn.running_mean": "layout", |
| "backbone.encoder.stages.2.downsample.bn.running_var": "layout", |
| "backbone.encoder.stages.2.downsample.bn.weight": "layout", |
| "backbone.encoder.stages.2.downsample.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.aggregation.0.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.aggregation.0.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.aggregation.0.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.aggregation.0.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.aggregation.0.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.aggregation.1.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.aggregation.1.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.aggregation.1.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.aggregation.1.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.aggregation.1.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.0.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.0.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.0.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.0.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.0.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.0.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.0.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.0.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.0.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.0.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.1.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.1.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.1.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.1.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.1.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.1.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.1.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.1.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.1.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.1.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.2.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.2.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.2.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.2.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.2.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.2.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.2.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.2.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.2.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.2.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.3.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.3.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.3.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.3.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.3.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.3.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.3.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.3.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.3.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.3.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.4.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.4.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.4.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.4.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.4.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.4.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.4.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.4.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.4.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.4.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.5.conv1.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.5.conv1.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.5.conv1.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.5.conv1.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.5.conv1.conv.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.5.conv2.bn.bias": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.5.conv2.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.5.conv2.bn.running_var": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.5.conv2.bn.weight": "layout", |
| "backbone.encoder.stages.3.blocks.0.layers.5.conv2.conv.weight": "layout", |
| "backbone.encoder.stages.3.downsample.bn.bias": "layout", |
| "backbone.encoder.stages.3.downsample.bn.running_mean": "layout", |
| "backbone.encoder.stages.3.downsample.bn.running_var": "layout", |
| "backbone.encoder.stages.3.downsample.bn.weight": "layout", |
| "backbone.encoder.stages.3.downsample.conv.weight": "layout", |
| "decoder.layers.0.encoder_attn.attention_weights.bias": "layout", |
| "decoder.layers.0.encoder_attn.attention_weights.weight": "layout", |
| "decoder.layers.0.encoder_attn.output_proj.bias": "layout", |
| "decoder.layers.0.encoder_attn.output_proj.weight": "layout", |
| "decoder.layers.0.encoder_attn.sampling_offsets.bias": "layout", |
| "decoder.layers.0.encoder_attn.sampling_offsets.weight": "layout", |
| "decoder.layers.0.encoder_attn.value_proj.bias": "layout", |
| "decoder.layers.0.encoder_attn.value_proj.weight": "layout", |
| "decoder.layers.0.encoder_attn_layer_norm.bias": "layout", |
| "decoder.layers.0.encoder_attn_layer_norm.weight": "layout", |
| "decoder.layers.0.fc1.bias": "layout", |
| "decoder.layers.0.fc1.weight": "layout", |
| "decoder.layers.0.fc2.bias": "layout", |
| "decoder.layers.0.fc2.weight": "layout", |
| "decoder.layers.0.final_layer_norm.bias": "layout", |
| "decoder.layers.0.final_layer_norm.weight": "layout", |
| "decoder.layers.0.self_attn.k_proj.bias": "layout", |
| "decoder.layers.0.self_attn.k_proj.weight": "layout", |
| "decoder.layers.0.self_attn.out_proj.bias": "layout", |
| "decoder.layers.0.self_attn.out_proj.weight": "layout", |
| "decoder.layers.0.self_attn.q_proj.bias": "layout", |
| "decoder.layers.0.self_attn.q_proj.weight": "layout", |
| "decoder.layers.0.self_attn.v_proj.bias": "layout", |
| "decoder.layers.0.self_attn.v_proj.weight": "layout", |
| "decoder.layers.0.self_attn_layer_norm.bias": "layout", |
| "decoder.layers.0.self_attn_layer_norm.weight": "layout", |
| "decoder.layers.1.encoder_attn.attention_weights.bias": "layout", |
| "decoder.layers.1.encoder_attn.attention_weights.weight": "layout", |
| "decoder.layers.1.encoder_attn.output_proj.bias": "layout", |
| "decoder.layers.1.encoder_attn.output_proj.weight": "layout", |
| "decoder.layers.1.encoder_attn.sampling_offsets.bias": "layout", |
| "decoder.layers.1.encoder_attn.sampling_offsets.weight": "layout", |
| "decoder.layers.1.encoder_attn.value_proj.bias": "layout", |
| "decoder.layers.1.encoder_attn.value_proj.weight": "layout", |
| "decoder.layers.1.encoder_attn_layer_norm.bias": "layout", |
| "decoder.layers.1.encoder_attn_layer_norm.weight": "layout", |
| "decoder.layers.1.fc1.bias": "layout", |
| "decoder.layers.1.fc1.weight": "layout", |
| "decoder.layers.1.fc2.bias": "layout", |
| "decoder.layers.1.fc2.weight": "layout", |
| "decoder.layers.1.final_layer_norm.bias": "layout", |
| "decoder.layers.1.final_layer_norm.weight": "layout", |
| "decoder.layers.1.self_attn.k_proj.bias": "layout", |
| "decoder.layers.1.self_attn.k_proj.weight": "layout", |
| "decoder.layers.1.self_attn.out_proj.bias": "layout", |
| "decoder.layers.1.self_attn.out_proj.weight": "layout", |
| "decoder.layers.1.self_attn.q_proj.bias": "layout", |
| "decoder.layers.1.self_attn.q_proj.weight": "layout", |
| "decoder.layers.1.self_attn.v_proj.bias": "layout", |
| "decoder.layers.1.self_attn.v_proj.weight": "layout", |
| "decoder.layers.1.self_attn_layer_norm.bias": "layout", |
| "decoder.layers.1.self_attn_layer_norm.weight": "layout", |
| "decoder.layers.2.encoder_attn.attention_weights.bias": "layout", |
| "decoder.layers.2.encoder_attn.attention_weights.weight": "layout", |
| "decoder.layers.2.encoder_attn.output_proj.bias": "layout", |
| "decoder.layers.2.encoder_attn.output_proj.weight": "layout", |
| "decoder.layers.2.encoder_attn.sampling_offsets.bias": "layout", |
| "decoder.layers.2.encoder_attn.sampling_offsets.weight": "layout", |
| "decoder.layers.2.encoder_attn.value_proj.bias": "layout", |
| "decoder.layers.2.encoder_attn.value_proj.weight": "layout", |
| "decoder.layers.2.encoder_attn_layer_norm.bias": "layout", |
| "decoder.layers.2.encoder_attn_layer_norm.weight": "layout", |
| "decoder.layers.2.fc1.bias": "layout", |
| "decoder.layers.2.fc1.weight": "layout", |
| "decoder.layers.2.fc2.bias": "layout", |
| "decoder.layers.2.fc2.weight": "layout", |
| "decoder.layers.2.final_layer_norm.bias": "layout", |
| "decoder.layers.2.final_layer_norm.weight": "layout", |
| "decoder.layers.2.self_attn.k_proj.bias": "layout", |
| "decoder.layers.2.self_attn.k_proj.weight": "layout", |
| "decoder.layers.2.self_attn.out_proj.bias": "layout", |
| "decoder.layers.2.self_attn.out_proj.weight": "layout", |
| "decoder.layers.2.self_attn.q_proj.bias": "layout", |
| "decoder.layers.2.self_attn.q_proj.weight": "layout", |
| "decoder.layers.2.self_attn.v_proj.bias": "layout", |
| "decoder.layers.2.self_attn.v_proj.weight": "layout", |
| "decoder.layers.2.self_attn_layer_norm.bias": "layout", |
| "decoder.layers.2.self_attn_layer_norm.weight": "layout", |
| "decoder.layers.3.encoder_attn.attention_weights.bias": "layout", |
| "decoder.layers.3.encoder_attn.attention_weights.weight": "layout", |
| "decoder.layers.3.encoder_attn.output_proj.bias": "layout", |
| "decoder.layers.3.encoder_attn.output_proj.weight": "layout", |
| "decoder.layers.3.encoder_attn.sampling_offsets.bias": "layout", |
| "decoder.layers.3.encoder_attn.sampling_offsets.weight": "layout", |
| "decoder.layers.3.encoder_attn.value_proj.bias": "layout", |
| "decoder.layers.3.encoder_attn.value_proj.weight": "layout", |
| "decoder.layers.3.encoder_attn_layer_norm.bias": "layout", |
| "decoder.layers.3.encoder_attn_layer_norm.weight": "layout", |
| "decoder.layers.3.fc1.bias": "layout", |
| "decoder.layers.3.fc1.weight": "layout", |
| "decoder.layers.3.fc2.bias": "layout", |
| "decoder.layers.3.fc2.weight": "layout", |
| "decoder.layers.3.final_layer_norm.bias": "layout", |
| "decoder.layers.3.final_layer_norm.weight": "layout", |
| "decoder.layers.3.self_attn.k_proj.bias": "layout", |
| "decoder.layers.3.self_attn.k_proj.weight": "layout", |
| "decoder.layers.3.self_attn.out_proj.bias": "layout", |
| "decoder.layers.3.self_attn.out_proj.weight": "layout", |
| "decoder.layers.3.self_attn.q_proj.bias": "layout", |
| "decoder.layers.3.self_attn.q_proj.weight": "layout", |
| "decoder.layers.3.self_attn.v_proj.bias": "layout", |
| "decoder.layers.3.self_attn.v_proj.weight": "layout", |
| "decoder.layers.3.self_attn_layer_norm.bias": "layout", |
| "decoder.layers.3.self_attn_layer_norm.weight": "layout", |
| "decoder.layers.4.encoder_attn.attention_weights.bias": "layout", |
| "decoder.layers.4.encoder_attn.attention_weights.weight": "layout", |
| "decoder.layers.4.encoder_attn.output_proj.bias": "layout", |
| "decoder.layers.4.encoder_attn.output_proj.weight": "layout", |
| "decoder.layers.4.encoder_attn.sampling_offsets.bias": "layout", |
| "decoder.layers.4.encoder_attn.sampling_offsets.weight": "layout", |
| "decoder.layers.4.encoder_attn.value_proj.bias": "layout", |
| "decoder.layers.4.encoder_attn.value_proj.weight": "layout", |
| "decoder.layers.4.encoder_attn_layer_norm.bias": "layout", |
| "decoder.layers.4.encoder_attn_layer_norm.weight": "layout", |
| "decoder.layers.4.fc1.bias": "layout", |
| "decoder.layers.4.fc1.weight": "layout", |
| "decoder.layers.4.fc2.bias": "layout", |
| "decoder.layers.4.fc2.weight": "layout", |
| "decoder.layers.4.final_layer_norm.bias": "layout", |
| "decoder.layers.4.final_layer_norm.weight": "layout", |
| "decoder.layers.4.self_attn.k_proj.bias": "layout", |
| "decoder.layers.4.self_attn.k_proj.weight": "layout", |
| "decoder.layers.4.self_attn.out_proj.bias": "layout", |
| "decoder.layers.4.self_attn.out_proj.weight": "layout", |
| "decoder.layers.4.self_attn.q_proj.bias": "layout", |
| "decoder.layers.4.self_attn.q_proj.weight": "layout", |
| "decoder.layers.4.self_attn.v_proj.bias": "layout", |
| "decoder.layers.4.self_attn.v_proj.weight": "layout", |
| "decoder.layers.4.self_attn_layer_norm.bias": "layout", |
| "decoder.layers.4.self_attn_layer_norm.weight": "layout", |
| "decoder.layers.5.encoder_attn.attention_weights.bias": "layout", |
| "decoder.layers.5.encoder_attn.attention_weights.weight": "layout", |
| "decoder.layers.5.encoder_attn.output_proj.bias": "layout", |
| "decoder.layers.5.encoder_attn.output_proj.weight": "layout", |
| "decoder.layers.5.encoder_attn.sampling_offsets.bias": "layout", |
| "decoder.layers.5.encoder_attn.sampling_offsets.weight": "layout", |
| "decoder.layers.5.encoder_attn.value_proj.bias": "layout", |
| "decoder.layers.5.encoder_attn.value_proj.weight": "layout", |
| "decoder.layers.5.encoder_attn_layer_norm.bias": "layout", |
| "decoder.layers.5.encoder_attn_layer_norm.weight": "layout", |
| "decoder.layers.5.fc1.bias": "layout", |
| "decoder.layers.5.fc1.weight": "layout", |
| "decoder.layers.5.fc2.bias": "layout", |
| "decoder.layers.5.fc2.weight": "layout", |
| "decoder.layers.5.final_layer_norm.bias": "layout", |
| "decoder.layers.5.final_layer_norm.weight": "layout", |
| "decoder.layers.5.self_attn.k_proj.bias": "layout", |
| "decoder.layers.5.self_attn.k_proj.weight": "layout", |
| "decoder.layers.5.self_attn.out_proj.bias": "layout", |
| "decoder.layers.5.self_attn.out_proj.weight": "layout", |
| "decoder.layers.5.self_attn.q_proj.bias": "layout", |
| "decoder.layers.5.self_attn.q_proj.weight": "layout", |
| "decoder.layers.5.self_attn.v_proj.bias": "layout", |
| "decoder.layers.5.self_attn.v_proj.weight": "layout", |
| "decoder.layers.5.self_attn_layer_norm.bias": "layout", |
| "decoder.layers.5.self_attn_layer_norm.weight": "layout", |
| "decoder.query_pos_head.layers.0.bias": "layout", |
| "decoder.query_pos_head.layers.0.weight": "layout", |
| "decoder.query_pos_head.layers.1.bias": "layout", |
| "decoder.query_pos_head.layers.1.weight": "layout", |
| "decoder_global_pointer.dense.bias": "layout", |
| "decoder_global_pointer.dense.weight": "layout", |
| "decoder_input_proj.0.bn.bias": "layout", |
| "decoder_input_proj.0.bn.running_mean": "layout", |
| "decoder_input_proj.0.bn.running_var": "layout", |
| "decoder_input_proj.0.bn.weight": "layout", |
| "decoder_input_proj.0.conv.weight": "layout", |
| "decoder_input_proj.1.bn.bias": "layout", |
| "decoder_input_proj.1.bn.running_mean": "layout", |
| "decoder_input_proj.1.bn.running_var": "layout", |
| "decoder_input_proj.1.bn.weight": "layout", |
| "decoder_input_proj.1.conv.weight": "layout", |
| "decoder_input_proj.2.bn.bias": "layout", |
| "decoder_input_proj.2.bn.running_mean": "layout", |
| "decoder_input_proj.2.bn.running_var": "layout", |
| "decoder_input_proj.2.bn.weight": "layout", |
| "decoder_input_proj.2.conv.weight": "layout", |
| "decoder_norm.bias": "layout", |
| "decoder_norm.weight": "layout", |
| "decoder_order_head.0.bias": "layout", |
| "decoder_order_head.0.weight": "layout", |
| "decoder_order_head.1.bias": "layout", |
| "decoder_order_head.1.weight": "layout", |
| "decoder_order_head.2.bias": "layout", |
| "decoder_order_head.2.weight": "layout", |
| "decoder_order_head.3.bias": "layout", |
| "decoder_order_head.3.weight": "layout", |
| "decoder_order_head.4.bias": "layout", |
| "decoder_order_head.4.weight": "layout", |
| "decoder_order_head.5.bias": "layout", |
| "decoder_order_head.5.weight": "layout", |
| "enc_bbox_head.layers.0.bias": "layout", |
| "enc_bbox_head.layers.0.weight": "layout", |
| "enc_bbox_head.layers.1.bias": "layout", |
| "enc_bbox_head.layers.1.weight": "layout", |
| "enc_bbox_head.layers.2.bias": "layout", |
| "enc_bbox_head.layers.2.weight": "layout", |
| "enc_output.fc.bias": "layout", |
| "enc_output.fc.weight": "layout", |
| "enc_output.ln.bias": "layout", |
| "enc_output.ln.weight": "layout", |
| "enc_score_head.bias": "layout", |
| "enc_score_head.weight": "layout", |
| "encoder.aifi.0.layers.0.fc1.bias": "layout", |
| "encoder.aifi.0.layers.0.fc1.weight": "layout", |
| "encoder.aifi.0.layers.0.fc2.bias": "layout", |
| "encoder.aifi.0.layers.0.fc2.weight": "layout", |
| "encoder.aifi.0.layers.0.final_layer_norm.bias": "layout", |
| "encoder.aifi.0.layers.0.final_layer_norm.weight": "layout", |
| "encoder.aifi.0.layers.0.self_attn.k_proj.bias": "layout", |
| "encoder.aifi.0.layers.0.self_attn.k_proj.weight": "layout", |
| "encoder.aifi.0.layers.0.self_attn.out_proj.bias": "layout", |
| "encoder.aifi.0.layers.0.self_attn.out_proj.weight": "layout", |
| "encoder.aifi.0.layers.0.self_attn.q_proj.bias": "layout", |
| "encoder.aifi.0.layers.0.self_attn.q_proj.weight": "layout", |
| "encoder.aifi.0.layers.0.self_attn.v_proj.bias": "layout", |
| "encoder.aifi.0.layers.0.self_attn.v_proj.weight": "layout", |
| "encoder.aifi.0.layers.0.self_attn_layer_norm.bias": "layout", |
| "encoder.aifi.0.layers.0.self_attn_layer_norm.weight": "layout", |
| "encoder.downsample_convs.0.bn.bias": "layout", |
| "encoder.downsample_convs.0.bn.running_mean": "layout", |
| "encoder.downsample_convs.0.bn.running_var": "layout", |
| "encoder.downsample_convs.0.bn.weight": "layout", |
| "encoder.downsample_convs.0.conv.weight": "layout", |
| "encoder.downsample_convs.1.bn.bias": "layout", |
| "encoder.downsample_convs.1.bn.running_mean": "layout", |
| "encoder.downsample_convs.1.bn.running_var": "layout", |
| "encoder.downsample_convs.1.bn.weight": "layout", |
| "encoder.downsample_convs.1.conv.weight": "layout", |
| "encoder.encoder_mask_lateral.bn.bias": "layout", |
| "encoder.encoder_mask_lateral.bn.running_mean": "layout", |
| "encoder.encoder_mask_lateral.bn.running_var": "layout", |
| "encoder.encoder_mask_lateral.bn.weight": "layout", |
| "encoder.encoder_mask_lateral.conv.weight": "layout", |
| "encoder.encoder_mask_output.base_conv.bn.bias": "layout", |
| "encoder.encoder_mask_output.base_conv.bn.running_mean": "layout", |
| "encoder.encoder_mask_output.base_conv.bn.running_var": "layout", |
| "encoder.encoder_mask_output.base_conv.bn.weight": "layout", |
| "encoder.encoder_mask_output.base_conv.conv.weight": "layout", |
| "encoder.encoder_mask_output.conv.bias": "layout", |
| "encoder.encoder_mask_output.conv.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.0.conv1.bn.bias": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.0.conv1.bn.running_mean": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.0.conv1.bn.running_var": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.0.conv1.bn.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.0.conv1.conv.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.0.conv2.bn.bias": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.0.conv2.bn.running_mean": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.0.conv2.bn.running_var": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.0.conv2.bn.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.0.conv2.conv.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.1.conv1.bn.bias": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.1.conv1.bn.running_mean": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.1.conv1.bn.running_var": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.1.conv1.bn.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.1.conv1.conv.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.1.conv2.bn.bias": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.1.conv2.bn.running_mean": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.1.conv2.bn.running_var": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.1.conv2.bn.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.1.conv2.conv.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.2.conv1.bn.bias": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.2.conv1.bn.running_mean": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.2.conv1.bn.running_var": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.2.conv1.bn.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.2.conv1.conv.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.2.conv2.bn.bias": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.2.conv2.bn.running_mean": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.2.conv2.bn.running_var": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.2.conv2.bn.weight": "layout", |
| "encoder.fpn_blocks.0.bottlenecks.2.conv2.conv.weight": "layout", |
| "encoder.fpn_blocks.0.conv1.bn.bias": "layout", |
| "encoder.fpn_blocks.0.conv1.bn.running_mean": "layout", |
| "encoder.fpn_blocks.0.conv1.bn.running_var": "layout", |
| "encoder.fpn_blocks.0.conv1.bn.weight": "layout", |
| "encoder.fpn_blocks.0.conv1.conv.weight": "layout", |
| "encoder.fpn_blocks.0.conv2.bn.bias": "layout", |
| "encoder.fpn_blocks.0.conv2.bn.running_mean": "layout", |
| "encoder.fpn_blocks.0.conv2.bn.running_var": "layout", |
| "encoder.fpn_blocks.0.conv2.bn.weight": "layout", |
| "encoder.fpn_blocks.0.conv2.conv.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.0.conv1.bn.bias": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.0.conv1.bn.running_mean": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.0.conv1.bn.running_var": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.0.conv1.bn.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.0.conv1.conv.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.0.conv2.bn.bias": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.0.conv2.bn.running_mean": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.0.conv2.bn.running_var": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.0.conv2.bn.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.0.conv2.conv.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.1.conv1.bn.bias": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.1.conv1.bn.running_mean": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.1.conv1.bn.running_var": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.1.conv1.bn.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.1.conv1.conv.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.1.conv2.bn.bias": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.1.conv2.bn.running_mean": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.1.conv2.bn.running_var": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.1.conv2.bn.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.1.conv2.conv.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.2.conv1.bn.bias": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.2.conv1.bn.running_mean": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.2.conv1.bn.running_var": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.2.conv1.bn.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.2.conv1.conv.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.2.conv2.bn.bias": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.2.conv2.bn.running_mean": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.2.conv2.bn.running_var": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.2.conv2.bn.weight": "layout", |
| "encoder.fpn_blocks.1.bottlenecks.2.conv2.conv.weight": "layout", |
| "encoder.fpn_blocks.1.conv1.bn.bias": "layout", |
| "encoder.fpn_blocks.1.conv1.bn.running_mean": "layout", |
| "encoder.fpn_blocks.1.conv1.bn.running_var": "layout", |
| "encoder.fpn_blocks.1.conv1.bn.weight": "layout", |
| "encoder.fpn_blocks.1.conv1.conv.weight": "layout", |
| "encoder.fpn_blocks.1.conv2.bn.bias": "layout", |
| "encoder.fpn_blocks.1.conv2.bn.running_mean": "layout", |
| "encoder.fpn_blocks.1.conv2.bn.running_var": "layout", |
| "encoder.fpn_blocks.1.conv2.bn.weight": "layout", |
| "encoder.fpn_blocks.1.conv2.conv.weight": "layout", |
| "encoder.lateral_convs.0.bn.bias": "layout", |
| "encoder.lateral_convs.0.bn.running_mean": "layout", |
| "encoder.lateral_convs.0.bn.running_var": "layout", |
| "encoder.lateral_convs.0.bn.weight": "layout", |
| "encoder.lateral_convs.0.conv.weight": "layout", |
| "encoder.lateral_convs.1.bn.bias": "layout", |
| "encoder.lateral_convs.1.bn.running_mean": "layout", |
| "encoder.lateral_convs.1.bn.running_var": "layout", |
| "encoder.lateral_convs.1.bn.weight": "layout", |
| "encoder.lateral_convs.1.conv.weight": "layout", |
| "encoder.mask_feature_head.output_conv.bn.bias": "layout", |
| "encoder.mask_feature_head.output_conv.bn.running_mean": "layout", |
| "encoder.mask_feature_head.output_conv.bn.running_var": "layout", |
| "encoder.mask_feature_head.output_conv.bn.weight": "layout", |
| "encoder.mask_feature_head.output_conv.conv.weight": "layout", |
| "encoder.mask_feature_head.scale_heads.0.layers.0.bn.bias": "layout", |
| "encoder.mask_feature_head.scale_heads.0.layers.0.bn.running_mean": "layout", |
| "encoder.mask_feature_head.scale_heads.0.layers.0.bn.running_var": "layout", |
| "encoder.mask_feature_head.scale_heads.0.layers.0.bn.weight": "layout", |
| "encoder.mask_feature_head.scale_heads.0.layers.0.conv.weight": "layout", |
| "encoder.mask_feature_head.scale_heads.1.layers.0.bn.bias": "layout", |
| "encoder.mask_feature_head.scale_heads.1.layers.0.bn.running_mean": "layout", |
| "encoder.mask_feature_head.scale_heads.1.layers.0.bn.running_var": "layout", |
| "encoder.mask_feature_head.scale_heads.1.layers.0.bn.weight": "layout", |
| "encoder.mask_feature_head.scale_heads.1.layers.0.conv.weight": "layout", |
| "encoder.mask_feature_head.scale_heads.2.layers.0.bn.bias": "layout", |
| "encoder.mask_feature_head.scale_heads.2.layers.0.bn.running_mean": "layout", |
| "encoder.mask_feature_head.scale_heads.2.layers.0.bn.running_var": "layout", |
| "encoder.mask_feature_head.scale_heads.2.layers.0.bn.weight": "layout", |
| "encoder.mask_feature_head.scale_heads.2.layers.0.conv.weight": "layout", |
| "encoder.mask_feature_head.scale_heads.2.layers.2.bn.bias": "layout", |
| "encoder.mask_feature_head.scale_heads.2.layers.2.bn.running_mean": "layout", |
| "encoder.mask_feature_head.scale_heads.2.layers.2.bn.running_var": "layout", |
| "encoder.mask_feature_head.scale_heads.2.layers.2.bn.weight": "layout", |
| "encoder.mask_feature_head.scale_heads.2.layers.2.conv.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.0.conv1.bn.bias": "layout", |
| "encoder.pan_blocks.0.bottlenecks.0.conv1.bn.running_mean": "layout", |
| "encoder.pan_blocks.0.bottlenecks.0.conv1.bn.running_var": "layout", |
| "encoder.pan_blocks.0.bottlenecks.0.conv1.bn.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.0.conv1.conv.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.0.conv2.bn.bias": "layout", |
| "encoder.pan_blocks.0.bottlenecks.0.conv2.bn.running_mean": "layout", |
| "encoder.pan_blocks.0.bottlenecks.0.conv2.bn.running_var": "layout", |
| "encoder.pan_blocks.0.bottlenecks.0.conv2.bn.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.0.conv2.conv.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.1.conv1.bn.bias": "layout", |
| "encoder.pan_blocks.0.bottlenecks.1.conv1.bn.running_mean": "layout", |
| "encoder.pan_blocks.0.bottlenecks.1.conv1.bn.running_var": "layout", |
| "encoder.pan_blocks.0.bottlenecks.1.conv1.bn.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.1.conv1.conv.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.1.conv2.bn.bias": "layout", |
| "encoder.pan_blocks.0.bottlenecks.1.conv2.bn.running_mean": "layout", |
| "encoder.pan_blocks.0.bottlenecks.1.conv2.bn.running_var": "layout", |
| "encoder.pan_blocks.0.bottlenecks.1.conv2.bn.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.1.conv2.conv.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.2.conv1.bn.bias": "layout", |
| "encoder.pan_blocks.0.bottlenecks.2.conv1.bn.running_mean": "layout", |
| "encoder.pan_blocks.0.bottlenecks.2.conv1.bn.running_var": "layout", |
| "encoder.pan_blocks.0.bottlenecks.2.conv1.bn.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.2.conv1.conv.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.2.conv2.bn.bias": "layout", |
| "encoder.pan_blocks.0.bottlenecks.2.conv2.bn.running_mean": "layout", |
| "encoder.pan_blocks.0.bottlenecks.2.conv2.bn.running_var": "layout", |
| "encoder.pan_blocks.0.bottlenecks.2.conv2.bn.weight": "layout", |
| "encoder.pan_blocks.0.bottlenecks.2.conv2.conv.weight": "layout", |
| "encoder.pan_blocks.0.conv1.bn.bias": "layout", |
| "encoder.pan_blocks.0.conv1.bn.running_mean": "layout", |
| "encoder.pan_blocks.0.conv1.bn.running_var": "layout", |
| "encoder.pan_blocks.0.conv1.bn.weight": "layout", |
| "encoder.pan_blocks.0.conv1.conv.weight": "layout", |
| "encoder.pan_blocks.0.conv2.bn.bias": "layout", |
| "encoder.pan_blocks.0.conv2.bn.running_mean": "layout", |
| "encoder.pan_blocks.0.conv2.bn.running_var": "layout", |
| "encoder.pan_blocks.0.conv2.bn.weight": "layout", |
| "encoder.pan_blocks.0.conv2.conv.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.0.conv1.bn.bias": "layout", |
| "encoder.pan_blocks.1.bottlenecks.0.conv1.bn.running_mean": "layout", |
| "encoder.pan_blocks.1.bottlenecks.0.conv1.bn.running_var": "layout", |
| "encoder.pan_blocks.1.bottlenecks.0.conv1.bn.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.0.conv1.conv.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.0.conv2.bn.bias": "layout", |
| "encoder.pan_blocks.1.bottlenecks.0.conv2.bn.running_mean": "layout", |
| "encoder.pan_blocks.1.bottlenecks.0.conv2.bn.running_var": "layout", |
| "encoder.pan_blocks.1.bottlenecks.0.conv2.bn.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.0.conv2.conv.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.1.conv1.bn.bias": "layout", |
| "encoder.pan_blocks.1.bottlenecks.1.conv1.bn.running_mean": "layout", |
| "encoder.pan_blocks.1.bottlenecks.1.conv1.bn.running_var": "layout", |
| "encoder.pan_blocks.1.bottlenecks.1.conv1.bn.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.1.conv1.conv.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.1.conv2.bn.bias": "layout", |
| "encoder.pan_blocks.1.bottlenecks.1.conv2.bn.running_mean": "layout", |
| "encoder.pan_blocks.1.bottlenecks.1.conv2.bn.running_var": "layout", |
| "encoder.pan_blocks.1.bottlenecks.1.conv2.bn.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.1.conv2.conv.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.2.conv1.bn.bias": "layout", |
| "encoder.pan_blocks.1.bottlenecks.2.conv1.bn.running_mean": "layout", |
| "encoder.pan_blocks.1.bottlenecks.2.conv1.bn.running_var": "layout", |
| "encoder.pan_blocks.1.bottlenecks.2.conv1.bn.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.2.conv1.conv.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.2.conv2.bn.bias": "layout", |
| "encoder.pan_blocks.1.bottlenecks.2.conv2.bn.running_mean": "layout", |
| "encoder.pan_blocks.1.bottlenecks.2.conv2.bn.running_var": "layout", |
| "encoder.pan_blocks.1.bottlenecks.2.conv2.bn.weight": "layout", |
| "encoder.pan_blocks.1.bottlenecks.2.conv2.conv.weight": "layout", |
| "encoder.pan_blocks.1.conv1.bn.bias": "layout", |
| "encoder.pan_blocks.1.conv1.bn.running_mean": "layout", |
| "encoder.pan_blocks.1.conv1.bn.running_var": "layout", |
| "encoder.pan_blocks.1.conv1.bn.weight": "layout", |
| "encoder.pan_blocks.1.conv1.conv.weight": "layout", |
| "encoder.pan_blocks.1.conv2.bn.bias": "layout", |
| "encoder.pan_blocks.1.conv2.bn.running_mean": "layout", |
| "encoder.pan_blocks.1.conv2.bn.running_var": "layout", |
| "encoder.pan_blocks.1.conv2.bn.weight": "layout", |
| "encoder.pan_blocks.1.conv2.conv.weight": "layout", |
| "encoder_input_proj.0.bn.bias": "layout", |
| "encoder_input_proj.0.bn.running_mean": "layout", |
| "encoder_input_proj.0.bn.running_var": "layout", |
| "encoder_input_proj.0.bn.weight": "layout", |
| "encoder_input_proj.0.conv.weight": "layout", |
| "encoder_input_proj.1.bn.bias": "layout", |
| "encoder_input_proj.1.bn.running_mean": "layout", |
| "encoder_input_proj.1.bn.running_var": "layout", |
| "encoder_input_proj.1.bn.weight": "layout", |
| "encoder_input_proj.1.conv.weight": "layout", |
| "encoder_input_proj.2.bn.bias": "layout", |
| "encoder_input_proj.2.bn.running_mean": "layout", |
| "encoder_input_proj.2.bn.running_var": "layout", |
| "encoder_input_proj.2.bn.weight": "layout", |
| "encoder_input_proj.2.conv.weight": "layout", |
| "mask_query_head.layers.0.bias": "layout", |
| "mask_query_head.layers.0.weight": "layout", |
| "mask_query_head.layers.1.bias": "layout", |
| "mask_query_head.layers.1.weight": "layout", |
| "mask_query_head.layers.2.bias": "layout", |
| "mask_query_head.layers.2.weight": "layout", |
| "language_model.model.embed_tokens.weight": "ocr", |
| "language_model.model.layers.0.input_layernorm.weight": "ocr", |
| "language_model.model.layers.0.linear_attn.A_log": "ocr", |
| "language_model.model.layers.0.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.0.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.0.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.0.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.0.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.0.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.0.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.0.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.0.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.0.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.0.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.0.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.1.input_layernorm.weight": "ocr", |
| "language_model.model.layers.1.linear_attn.A_log": "ocr", |
| "language_model.model.layers.1.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.1.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.1.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.1.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.1.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.1.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.1.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.1.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.1.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.1.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.1.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.1.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.10.input_layernorm.weight": "ocr", |
| "language_model.model.layers.10.linear_attn.A_log": "ocr", |
| "language_model.model.layers.10.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.10.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.10.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.10.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.10.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.10.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.10.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.10.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.10.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.10.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.10.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.10.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.11.input_layernorm.weight": "ocr", |
| "language_model.model.layers.11.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.11.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.11.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.11.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.11.self_attn.k_norm.weight": "ocr", |
| "language_model.model.layers.11.self_attn.k_proj.weight": "ocr", |
| "language_model.model.layers.11.self_attn.o_proj.weight": "ocr", |
| "language_model.model.layers.11.self_attn.q_norm.weight": "ocr", |
| "language_model.model.layers.11.self_attn.q_proj.weight": "ocr", |
| "language_model.model.layers.11.self_attn.v_proj.weight": "ocr", |
| "language_model.model.layers.12.input_layernorm.weight": "ocr", |
| "language_model.model.layers.12.linear_attn.A_log": "ocr", |
| "language_model.model.layers.12.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.12.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.12.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.12.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.12.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.12.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.12.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.12.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.12.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.12.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.12.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.13.input_layernorm.weight": "ocr", |
| "language_model.model.layers.13.linear_attn.A_log": "ocr", |
| "language_model.model.layers.13.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.13.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.13.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.13.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.13.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.13.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.13.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.13.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.13.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.13.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.13.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.14.input_layernorm.weight": "ocr", |
| "language_model.model.layers.14.linear_attn.A_log": "ocr", |
| "language_model.model.layers.14.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.14.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.14.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.14.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.14.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.14.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.14.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.14.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.14.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.14.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.14.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.14.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.15.input_layernorm.weight": "ocr", |
| "language_model.model.layers.15.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.15.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.15.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.15.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.15.self_attn.k_norm.weight": "ocr", |
| "language_model.model.layers.15.self_attn.k_proj.weight": "ocr", |
| "language_model.model.layers.15.self_attn.o_proj.weight": "ocr", |
| "language_model.model.layers.15.self_attn.q_norm.weight": "ocr", |
| "language_model.model.layers.15.self_attn.q_proj.weight": "ocr", |
| "language_model.model.layers.15.self_attn.v_proj.weight": "ocr", |
| "language_model.model.layers.16.input_layernorm.weight": "ocr", |
| "language_model.model.layers.16.linear_attn.A_log": "ocr", |
| "language_model.model.layers.16.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.16.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.16.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.16.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.16.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.16.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.16.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.16.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.16.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.16.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.16.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.16.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.17.input_layernorm.weight": "ocr", |
| "language_model.model.layers.17.linear_attn.A_log": "ocr", |
| "language_model.model.layers.17.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.17.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.17.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.17.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.17.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.17.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.17.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.17.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.17.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.17.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.17.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.17.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.18.input_layernorm.weight": "ocr", |
| "language_model.model.layers.18.linear_attn.A_log": "ocr", |
| "language_model.model.layers.18.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.18.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.18.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.18.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.18.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.18.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.18.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.18.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.18.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.18.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.18.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.19.input_layernorm.weight": "ocr", |
| "language_model.model.layers.19.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.19.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.19.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.19.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.19.self_attn.k_norm.weight": "ocr", |
| "language_model.model.layers.19.self_attn.k_proj.weight": "ocr", |
| "language_model.model.layers.19.self_attn.o_proj.weight": "ocr", |
| "language_model.model.layers.19.self_attn.q_norm.weight": "ocr", |
| "language_model.model.layers.19.self_attn.q_proj.weight": "ocr", |
| "language_model.model.layers.19.self_attn.v_proj.weight": "ocr", |
| "language_model.model.layers.2.input_layernorm.weight": "ocr", |
| "language_model.model.layers.2.linear_attn.A_log": "ocr", |
| "language_model.model.layers.2.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.2.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.2.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.2.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.2.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.2.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.2.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.2.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.2.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.2.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.2.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.2.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.20.input_layernorm.weight": "ocr", |
| "language_model.model.layers.20.linear_attn.A_log": "ocr", |
| "language_model.model.layers.20.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.20.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.20.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.20.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.20.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.20.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.20.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.20.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.20.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.20.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.20.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.20.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.21.input_layernorm.weight": "ocr", |
| "language_model.model.layers.21.linear_attn.A_log": "ocr", |
| "language_model.model.layers.21.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.21.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.21.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.21.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.21.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.21.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.21.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.21.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.21.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.21.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.21.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.21.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.22.input_layernorm.weight": "ocr", |
| "language_model.model.layers.22.linear_attn.A_log": "ocr", |
| "language_model.model.layers.22.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.22.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.22.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.22.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.22.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.22.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.22.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.22.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.22.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.22.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.22.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.22.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.23.input_layernorm.weight": "ocr", |
| "language_model.model.layers.23.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.23.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.23.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.23.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.23.self_attn.k_norm.weight": "ocr", |
| "language_model.model.layers.23.self_attn.k_proj.weight": "ocr", |
| "language_model.model.layers.23.self_attn.o_proj.weight": "ocr", |
| "language_model.model.layers.23.self_attn.q_norm.weight": "ocr", |
| "language_model.model.layers.23.self_attn.q_proj.weight": "ocr", |
| "language_model.model.layers.23.self_attn.v_proj.weight": "ocr", |
| "language_model.model.layers.3.input_layernorm.weight": "ocr", |
| "language_model.model.layers.3.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.3.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.3.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.3.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.3.self_attn.k_norm.weight": "ocr", |
| "language_model.model.layers.3.self_attn.k_proj.weight": "ocr", |
| "language_model.model.layers.3.self_attn.o_proj.weight": "ocr", |
| "language_model.model.layers.3.self_attn.q_norm.weight": "ocr", |
| "language_model.model.layers.3.self_attn.q_proj.weight": "ocr", |
| "language_model.model.layers.3.self_attn.v_proj.weight": "ocr", |
| "language_model.model.layers.4.input_layernorm.weight": "ocr", |
| "language_model.model.layers.4.linear_attn.A_log": "ocr", |
| "language_model.model.layers.4.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.4.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.4.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.4.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.4.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.4.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.4.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.4.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.4.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.4.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.4.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.4.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.5.input_layernorm.weight": "ocr", |
| "language_model.model.layers.5.linear_attn.A_log": "ocr", |
| "language_model.model.layers.5.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.5.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.5.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.5.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.5.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.5.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.5.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.5.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.5.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.5.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.5.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.5.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.6.input_layernorm.weight": "ocr", |
| "language_model.model.layers.6.linear_attn.A_log": "ocr", |
| "language_model.model.layers.6.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.6.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.6.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.6.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.6.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.6.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.6.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.6.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.6.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.6.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.6.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.6.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.7.input_layernorm.weight": "ocr", |
| "language_model.model.layers.7.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.7.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.7.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.7.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.7.self_attn.k_norm.weight": "ocr", |
| "language_model.model.layers.7.self_attn.k_proj.weight": "ocr", |
| "language_model.model.layers.7.self_attn.o_proj.weight": "ocr", |
| "language_model.model.layers.7.self_attn.q_norm.weight": "ocr", |
| "language_model.model.layers.7.self_attn.q_proj.weight": "ocr", |
| "language_model.model.layers.7.self_attn.v_proj.weight": "ocr", |
| "language_model.model.layers.8.input_layernorm.weight": "ocr", |
| "language_model.model.layers.8.linear_attn.A_log": "ocr", |
| "language_model.model.layers.8.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.8.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.8.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.8.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.8.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.8.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.8.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.8.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.8.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.8.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.8.post_attention_layernorm.weight": "ocr", |
| "language_model.model.layers.9.input_layernorm.weight": "ocr", |
| "language_model.model.layers.9.linear_attn.A_log": "ocr", |
| "language_model.model.layers.9.linear_attn.conv1d.weight": "ocr", |
| "language_model.model.layers.9.linear_attn.dt_bias": "ocr", |
| "language_model.model.layers.9.linear_attn.in_proj_a.weight": "ocr", |
| "language_model.model.layers.9.linear_attn.in_proj_b.weight": "ocr", |
| "language_model.model.layers.9.linear_attn.in_proj_qkv.weight": "ocr", |
| "language_model.model.layers.9.linear_attn.in_proj_z.weight": "ocr", |
| "language_model.model.layers.9.linear_attn.norm.weight": "ocr", |
| "language_model.model.layers.9.linear_attn.out_proj.weight": "ocr", |
| "language_model.model.layers.9.mlp.down_proj.weight": "ocr", |
| "language_model.model.layers.9.mlp.gate_proj.weight": "ocr", |
| "language_model.model.layers.9.mlp.up_proj.weight": "ocr", |
| "language_model.model.layers.9.post_attention_layernorm.weight": "ocr", |
| "language_model.model.norm.weight": "ocr", |
| "vision_tower.blocks.0.attn.proj.bias": "ocr", |
| "vision_tower.blocks.0.attn.proj.weight": "ocr", |
| "vision_tower.blocks.0.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.0.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.0.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.0.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.0.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.0.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.0.norm1.bias": "ocr", |
| "vision_tower.blocks.0.norm1.weight": "ocr", |
| "vision_tower.blocks.0.norm2.bias": "ocr", |
| "vision_tower.blocks.0.norm2.weight": "ocr", |
| "vision_tower.blocks.1.attn.proj.bias": "ocr", |
| "vision_tower.blocks.1.attn.proj.weight": "ocr", |
| "vision_tower.blocks.1.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.1.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.1.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.1.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.1.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.1.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.1.norm1.bias": "ocr", |
| "vision_tower.blocks.1.norm1.weight": "ocr", |
| "vision_tower.blocks.1.norm2.bias": "ocr", |
| "vision_tower.blocks.1.norm2.weight": "ocr", |
| "vision_tower.blocks.10.attn.proj.bias": "ocr", |
| "vision_tower.blocks.10.attn.proj.weight": "ocr", |
| "vision_tower.blocks.10.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.10.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.10.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.10.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.10.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.10.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.10.norm1.bias": "ocr", |
| "vision_tower.blocks.10.norm1.weight": "ocr", |
| "vision_tower.blocks.10.norm2.bias": "ocr", |
| "vision_tower.blocks.10.norm2.weight": "ocr", |
| "vision_tower.blocks.11.attn.proj.bias": "ocr", |
| "vision_tower.blocks.11.attn.proj.weight": "ocr", |
| "vision_tower.blocks.11.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.11.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.11.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.11.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.11.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.11.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.11.norm1.bias": "ocr", |
| "vision_tower.blocks.11.norm1.weight": "ocr", |
| "vision_tower.blocks.11.norm2.bias": "ocr", |
| "vision_tower.blocks.11.norm2.weight": "ocr", |
| "vision_tower.blocks.2.attn.proj.bias": "ocr", |
| "vision_tower.blocks.2.attn.proj.weight": "ocr", |
| "vision_tower.blocks.2.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.2.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.2.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.2.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.2.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.2.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.2.norm1.bias": "ocr", |
| "vision_tower.blocks.2.norm1.weight": "ocr", |
| "vision_tower.blocks.2.norm2.bias": "ocr", |
| "vision_tower.blocks.2.norm2.weight": "ocr", |
| "vision_tower.blocks.3.attn.proj.bias": "ocr", |
| "vision_tower.blocks.3.attn.proj.weight": "ocr", |
| "vision_tower.blocks.3.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.3.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.3.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.3.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.3.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.3.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.3.norm1.bias": "ocr", |
| "vision_tower.blocks.3.norm1.weight": "ocr", |
| "vision_tower.blocks.3.norm2.bias": "ocr", |
| "vision_tower.blocks.3.norm2.weight": "ocr", |
| "vision_tower.blocks.4.attn.proj.bias": "ocr", |
| "vision_tower.blocks.4.attn.proj.weight": "ocr", |
| "vision_tower.blocks.4.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.4.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.4.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.4.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.4.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.4.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.4.norm1.bias": "ocr", |
| "vision_tower.blocks.4.norm1.weight": "ocr", |
| "vision_tower.blocks.4.norm2.bias": "ocr", |
| "vision_tower.blocks.4.norm2.weight": "ocr", |
| "vision_tower.blocks.5.attn.proj.bias": "ocr", |
| "vision_tower.blocks.5.attn.proj.weight": "ocr", |
| "vision_tower.blocks.5.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.5.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.5.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.5.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.5.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.5.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.5.norm1.bias": "ocr", |
| "vision_tower.blocks.5.norm1.weight": "ocr", |
| "vision_tower.blocks.5.norm2.bias": "ocr", |
| "vision_tower.blocks.5.norm2.weight": "ocr", |
| "vision_tower.blocks.6.attn.proj.bias": "ocr", |
| "vision_tower.blocks.6.attn.proj.weight": "ocr", |
| "vision_tower.blocks.6.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.6.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.6.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.6.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.6.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.6.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.6.norm1.bias": "ocr", |
| "vision_tower.blocks.6.norm1.weight": "ocr", |
| "vision_tower.blocks.6.norm2.bias": "ocr", |
| "vision_tower.blocks.6.norm2.weight": "ocr", |
| "vision_tower.blocks.7.attn.proj.bias": "ocr", |
| "vision_tower.blocks.7.attn.proj.weight": "ocr", |
| "vision_tower.blocks.7.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.7.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.7.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.7.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.7.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.7.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.7.norm1.bias": "ocr", |
| "vision_tower.blocks.7.norm1.weight": "ocr", |
| "vision_tower.blocks.7.norm2.bias": "ocr", |
| "vision_tower.blocks.7.norm2.weight": "ocr", |
| "vision_tower.blocks.8.attn.proj.bias": "ocr", |
| "vision_tower.blocks.8.attn.proj.weight": "ocr", |
| "vision_tower.blocks.8.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.8.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.8.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.8.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.8.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.8.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.8.norm1.bias": "ocr", |
| "vision_tower.blocks.8.norm1.weight": "ocr", |
| "vision_tower.blocks.8.norm2.bias": "ocr", |
| "vision_tower.blocks.8.norm2.weight": "ocr", |
| "vision_tower.blocks.9.attn.proj.bias": "ocr", |
| "vision_tower.blocks.9.attn.proj.weight": "ocr", |
| "vision_tower.blocks.9.attn.qkv.bias": "ocr", |
| "vision_tower.blocks.9.attn.qkv.weight": "ocr", |
| "vision_tower.blocks.9.mlp.linear_fc1.bias": "ocr", |
| "vision_tower.blocks.9.mlp.linear_fc1.weight": "ocr", |
| "vision_tower.blocks.9.mlp.linear_fc2.bias": "ocr", |
| "vision_tower.blocks.9.mlp.linear_fc2.weight": "ocr", |
| "vision_tower.blocks.9.norm1.bias": "ocr", |
| "vision_tower.blocks.9.norm1.weight": "ocr", |
| "vision_tower.blocks.9.norm2.bias": "ocr", |
| "vision_tower.blocks.9.norm2.weight": "ocr", |
| "vision_tower.merger.linear_fc1.bias": "ocr", |
| "vision_tower.merger.linear_fc1.weight": "ocr", |
| "vision_tower.merger.linear_fc2.bias": "ocr", |
| "vision_tower.merger.linear_fc2.weight": "ocr", |
| "vision_tower.merger.norm.bias": "ocr", |
| "vision_tower.merger.norm.weight": "ocr", |
| "vision_tower.patch_embed.proj.bias": "ocr", |
| "vision_tower.patch_embed.proj.weight": "ocr", |
| "vision_tower.pos_embed.weight": "ocr" |
| } |
| } |
|
|
