| { |
| "adjacency_loss_coef": 1.0, |
| "anchor_num_heads": 4, |
| "anchor_num_layers": 2, |
| "backbone_type": "deberta_2d", |
| "bos_token_id": 1, |
| "cat_loss_coef": 1.0, |
| "cat_parent_token": "[SCHEMA]", |
| "cat_token": "[CLASS]", |
| "cat_token_index": 128003, |
| "child_token": "[FIELD]", |
| "child_token_index": 128005, |
| "class_token_index": 128001, |
| "classification_config": { |
| "anchor_context_gate_init": 0.1, |
| "anchor_context_gate_trainable": true, |
| "anchor_cross_attention_bias": null, |
| "anchor_layer": null, |
| "anchor_memory_position": null, |
| "anchor_memory_position_usage": null, |
| "anchor_mode": "parent", |
| "anchor_modeling": "linear", |
| "anchor_normalization": "none", |
| "anchor_query_position": null, |
| "anchor_refine_heads": 8, |
| "anchor_refine_layer_scale_init": null, |
| "anchor_refine_layers": 0, |
| "anchor_refine_norm": "post_norm", |
| "anchor_refinement": null, |
| "anchor_self_attention_bias": null, |
| "cat_token_index": 128003, |
| "embed_cat_token": true, |
| "embed_parent_token": true, |
| "feature_anchor_mlp": false, |
| "feature_anchor_mlp_hidden_multiplier": 1, |
| "focal_loss_alpha": 0.8, |
| "focal_loss_gamma": -1.0, |
| "focal_loss_prob_margin": 0.0, |
| "loss_coef": 1.0, |
| "parent_token_index": 128002, |
| "pooling_type": "cls", |
| "scorer_type": "dot" |
| }, |
| "classifier_layer": null, |
| "count_config": null, |
| "count_layer": null, |
| "count_loss_coef": 1.0, |
| "count_mode": "regression", |
| "dropout": 0.25, |
| "embed_cat_token": true, |
| "embed_child_token": true, |
| "embed_ent_token": true, |
| "embed_parent_token": true, |
| "embed_rel_token": true, |
| "embedding_config": { |
| "encoder_dropout": 0.0, |
| "loss_coef": 1.0, |
| "loss_fn": "mse", |
| "margin": 0.0, |
| "pooling_type": "cls", |
| "projection_dim": 1024, |
| "projection_dropout": 0.0, |
| "similarity_fn": "cosine" |
| }, |
| "embedding_loss_coef": 1.0, |
| "encoder_config": { |
| "_name_or_path": "knowledgator/DeBERTa-large-joint-3000", |
| "architectures": [ |
| "FlashDebertaV2ForContextPredictionTraining" |
| ], |
| "attention_probs_dropout_prob": 0.0, |
| "attn_kernel": "flash", |
| "bos_token_id": null, |
| "chunk_size_feed_forward": 0, |
| "coordinate_size": 128, |
| "dtype": "bfloat16", |
| "eos_token_id": null, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.0, |
| "hidden_size": 1024, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "is_encoder_decoder": false, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1 |
| }, |
| "layer_norm_eps": 1e-07, |
| "layout_bias_propagation": "all_layers", |
| "layout_embedding_type": "absolute", |
| "layout_max_relative_positions": 1024, |
| "layout_position_buckets": 32, |
| "layout_relative_attention": false, |
| "legacy": true, |
| "max_2d_position_embeddings": 1024, |
| "max_page_embeddings": 1024, |
| "max_position_embeddings": 512, |
| "max_relative_positions": -1, |
| "model_type": "layout-deberta", |
| "norm_rel_ebd": "layer_norm", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 24, |
| "output_attentions": false, |
| "output_hidden_states": false, |
| "pad_token_id": 0, |
| "pooler_dropout": 0.0, |
| "pooler_hidden_act": "gelu", |
| "pooler_hidden_size": 1024, |
| "pos_att_type": [ |
| "p2c", |
| "c2p" |
| ], |
| "position_biased_input": false, |
| "position_buckets": 256, |
| "problem_type": null, |
| "relative_attention": true, |
| "return_dict": true, |
| "shape_size": 64, |
| "share_att_key": true, |
| "spatial_embedding_type": "absolute", |
| "tie_word_embeddings": true, |
| "type_vocab_size": 0, |
| "vocab_size": 128008 |
| }, |
| "ent_token": "[ENTITY]", |
| "eos_token_id": 2, |
| "fine_tune": true, |
| "fuse_layers": false, |
| "groups_layer": "fixed", |
| "groups_loss_coef": 1.0, |
| "hidden_size": 1024, |
| "image_size": 224, |
| "joint_relex_config": { |
| "adjacency_loss_coef": 1.0, |
| "anchor_context_gate_init": 0.1, |
| "anchor_context_gate_trainable": true, |
| "anchor_cross_attention_bias": null, |
| "anchor_layer": null, |
| "anchor_memory_position": null, |
| "anchor_memory_position_usage": null, |
| "anchor_mode": "fixed", |
| "anchor_modeling": "linear", |
| "anchor_normalization": "none", |
| "anchor_num_heads": 4, |
| "anchor_num_layers": 2, |
| "anchor_query_position": null, |
| "anchor_refine_heads": 8, |
| "anchor_refine_layer_scale_init": null, |
| "anchor_refine_layers": 0, |
| "anchor_refine_norm": "post_norm", |
| "anchor_refinement": null, |
| "anchor_self_attention_bias": null, |
| "embed_parent_token": true, |
| "embed_rel_token": true, |
| "feature_anchor_mlp": false, |
| "feature_anchor_mlp_hidden_multiplier": 1, |
| "focal_loss_alpha": 0.8, |
| "focal_loss_gamma": -1.0, |
| "focal_loss_prob_margin": 0.0, |
| "loss_coef": 1.0, |
| "max_count": 20, |
| "max_relation_entities": null, |
| "max_relation_span_width": null, |
| "neg_spans_ratio": 1.0, |
| "num_fixed_slots": 10, |
| "parent_token_index": -1, |
| "rel_token_index": 128004, |
| "relation_focal_loss_alpha": 0.8, |
| "relation_focal_loss_gamma": 2, |
| "relation_focal_loss_prob_margin": 0.0, |
| "relation_loss_coef": 1.0, |
| "relation_loss_reduction": "mean", |
| "relation_neighbor_chunk_size": 512, |
| "relation_span_nms": false, |
| "relation_top_k_neighbors": null, |
| "relations_layer": null, |
| "represent_spans": false, |
| "span_loss_coef": 1.0, |
| "span_loss_reduction": "mean", |
| "triples_layer": null |
| }, |
| "labels_encoder": null, |
| "labels_encoder_config": null, |
| "layout_image_tokens": true, |
| "max_count": 20, |
| "max_len": 16384, |
| "max_neg_type_ratio": 1, |
| "max_page_embeddings": 1024, |
| "max_types": 128, |
| "max_width": 12, |
| "media_parent_embedding_source": "fixed", |
| "model_name": "knowledgator/DeBERTa-large-joint-3000", |
| "model_type": "gliformer-layout", |
| "model_variant": "layout", |
| "multimodal_fusion": "uni-encoder", |
| "name": "gliformer", |
| "neg_spans_ratio": 1.0, |
| "ner_config": { |
| "anchor_context_gate_init": 0.1, |
| "anchor_context_gate_trainable": true, |
| "anchor_cross_attention_bias": null, |
| "anchor_layer": null, |
| "anchor_memory_position": null, |
| "anchor_memory_position_usage": null, |
| "anchor_mode": "parent", |
| "anchor_modeling": "linear", |
| "anchor_normalization": "none", |
| "anchor_query_position": null, |
| "anchor_refine_heads": 8, |
| "anchor_refine_layer_scale_init": null, |
| "anchor_refine_layers": 0, |
| "anchor_refine_norm": "post_norm", |
| "anchor_refinement": null, |
| "anchor_self_attention_bias": null, |
| "embed_parent_token": true, |
| "feature_anchor_mlp": false, |
| "feature_anchor_mlp_hidden_multiplier": 1, |
| "focal_loss_alpha": 0.8, |
| "focal_loss_gamma": -1, |
| "focal_loss_prob_margin": 0.0, |
| "loss_coef": 1.0, |
| "neg_spans_ratio": 1.0, |
| "parent_token_index": 128002, |
| "represent_spans": false, |
| "span_loss_coef": 1.0, |
| "span_loss_reduction": "mean" |
| }, |
| "ner_loss_coef": 1.0, |
| "ner_parent_token": "[SCHEMA]", |
| "num_post_fusion_layers": 1, |
| "num_rnn_layers": 1, |
| "obj_token": "[OBJECT]", |
| "open_rel_parent_token": "[SCHEMA]", |
| "open_relex_config": null, |
| "pad_token_id": 0, |
| "parent_token": "[SCHEMA]", |
| "parent_token_index": 128002, |
| "per_task_parents": false, |
| "post_fusion_schema": "", |
| "projector_hidden_act": "gelu", |
| "rel_mode": "adjacency", |
| "rel_token": "[RELATION]", |
| "rel_token_index": 128004, |
| "relation_loss_coef": 1.0, |
| "relations_config": { |
| "adjacency_loss_coef": 1.0, |
| "anchor_context_gate_init": 0.1, |
| "anchor_context_gate_trainable": true, |
| "anchor_cross_attention_bias": null, |
| "anchor_layer": null, |
| "anchor_memory_position": null, |
| "anchor_memory_position_usage": null, |
| "anchor_mode": "fixed", |
| "anchor_modeling": "linear", |
| "anchor_normalization": "none", |
| "anchor_num_heads": 4, |
| "anchor_num_layers": 2, |
| "anchor_query_position": null, |
| "anchor_refine_heads": 8, |
| "anchor_refine_layer_scale_init": null, |
| "anchor_refine_layers": 0, |
| "anchor_refine_norm": "post_norm", |
| "anchor_refinement": null, |
| "anchor_self_attention_bias": null, |
| "embed_parent_token": true, |
| "embed_rel_token": true, |
| "feature_anchor_mlp": false, |
| "feature_anchor_mlp_hidden_multiplier": 1, |
| "focal_loss_alpha": 0.8, |
| "focal_loss_gamma": -1.0, |
| "focal_loss_prob_margin": 0.0, |
| "loss_coef": 1.0, |
| "max_count": 20, |
| "max_relation_entities": null, |
| "max_relation_span_width": null, |
| "neg_spans_ratio": 1.0, |
| "num_fixed_slots": 10, |
| "parent_token_index": -1, |
| "rel_token_index": 128004, |
| "relation_focal_loss_alpha": 0.8, |
| "relation_focal_loss_gamma": 2, |
| "relation_focal_loss_prob_margin": 0.0, |
| "relation_loss_coef": 1.0, |
| "relation_loss_reduction": "mean", |
| "relation_neighbor_chunk_size": 512, |
| "relation_span_nms": false, |
| "relation_top_k_neighbors": null, |
| "relations_layer": null, |
| "represent_spans": false, |
| "span_loss_coef": 1.0, |
| "span_loss_reduction": "mean", |
| "triples_layer": null |
| }, |
| "relations_layer": null, |
| "represent_spans": false, |
| "sep_token": "[SEP]", |
| "seq_token": "[SEQ]", |
| "shared_anchor_modeling": null, |
| "shared_anchor_refine_heads": 8, |
| "shared_anchor_refine_layers": 0, |
| "shared_anchor_refinement": null, |
| "span_loss_coef": 1.0, |
| "span_mode": "markerV0", |
| "struct_parent_token": "[SCHEMA]", |
| "structuring_child_token": "<<CHILD>>", |
| "structuring_config": { |
| "anchor_context_gate_init": 0.1, |
| "anchor_context_gate_trainable": true, |
| "anchor_cross_attention_bias": { |
| "params": { |
| "sigma": 0.5, |
| "units": "query_steps", |
| "weight": 1.0 |
| }, |
| "type": "gaussian_distance" |
| }, |
| "anchor_layer": { |
| "params": { |
| "num_slots": 100 |
| }, |
| "type": "fixed" |
| }, |
| "anchor_memory_position": { |
| "params": {}, |
| "type": "fourier" |
| }, |
| "anchor_memory_position_usage": "keys_and_values", |
| "anchor_mode": "fixed_transformer", |
| "anchor_modeling": "linear", |
| "anchor_normalization": "center_rms", |
| "anchor_num_heads": 4, |
| "anchor_num_layers": 2, |
| "anchor_objectness": true, |
| "anchor_objectness_loss_coef": 1.0, |
| "anchor_objectness_threshold": 0.5, |
| "anchor_query_position": { |
| "params": {}, |
| "type": "fourier" |
| }, |
| "anchor_refine_heads": 8, |
| "anchor_refine_layer_scale_init": null, |
| "anchor_refine_layers": 0, |
| "anchor_refine_norm": "post_norm", |
| "anchor_refinement": { |
| "params": { |
| "layer_scale_init": 0.1, |
| "norm_style": "pre_norm", |
| "num_heads": 8, |
| "num_layers": 2 |
| }, |
| "type": "cross_attention" |
| }, |
| "anchor_relations_focal_loss_alpha": 0.75, |
| "anchor_relations_focal_loss_gamma": null, |
| "anchor_relations_focal_loss_prob_margin": null, |
| "anchor_relations_layer": "mlp", |
| "anchor_relations_loss_coef": 1.0, |
| "anchor_relations_threshold": 0.5, |
| "anchor_self_attention_bias": null, |
| "assignment_loss_coef": 1.0, |
| "bio_loss_reduction": "mean", |
| "child_token_index": 128005, |
| "embed_child_token": true, |
| "embed_parent_token": true, |
| "entity_loss_coef": 1.0, |
| "feature_anchor_mlp": false, |
| "feature_anchor_mlp_hidden_multiplier": 1, |
| "focal_loss_alpha": 0.75, |
| "focal_loss_gamma": -1, |
| "focal_loss_prob_margin": 0.0, |
| "head_type": "structuring", |
| "log_loss_stats": false, |
| "log_loss_stats_every": 50, |
| "loss_coef": 1.0, |
| "masking": "none", |
| "matcher_dice_cost": 1.0, |
| "matcher_membership_cost": 1.0, |
| "matcher_membership_temperature": 1.0, |
| "matcher_objectness_cost": 0.5, |
| "matcher_objectness_temperature": 1.0, |
| "matching_focal_loss_alpha": 0.99, |
| "matching_focal_loss_gamma": null, |
| "matching_focal_loss_prob_margin": null, |
| "max_count": 100, |
| "memory_position_embedding_kwargs": {}, |
| "memory_position_embedding_type": "none", |
| "memory_position_in_values": false, |
| "multi_level": true, |
| "neg_spans_ratio": 1.0, |
| "negatives": 1.0, |
| "ner_focal_loss_alpha": 0.75, |
| "ner_focal_loss_gamma": null, |
| "ner_focal_loss_prob_margin": null, |
| "num_fixed_slots": 10, |
| "objectness_focal_loss_alpha": 0.5, |
| "objectness_focal_loss_gamma": null, |
| "objectness_focal_loss_prob_margin": null, |
| "parent_token_index": 128002, |
| "position_bucket_attention_bias_type": "none", |
| "position_bucket_attention_bias_weight": 1.0, |
| "position_bucket_attention_sigma": 0.5, |
| "position_bucket_normalization": "none", |
| "query_position_embedding_kwargs": {}, |
| "query_position_embedding_type": "none", |
| "represent_spans": true, |
| "reuse_ner_head": true, |
| "span_loss_coef": 1.0, |
| "span_loss_reduction": "mean", |
| "structure_mode": { |
| "decoder": null, |
| "decoder_options": {}, |
| "params": {}, |
| "processor": null, |
| "processor_options": {}, |
| "type": "multi_level" |
| }, |
| "use_anchor_matching": true |
| }, |
| "structuring_end_token": "<<END>>", |
| "structuring_loss_coef": 1.0, |
| "subtoken_pooling": "first", |
| "token_loss_coef": 1.0, |
| "transformers_version": "5.16.1", |
| "triples_layer": null, |
| "use_layout": true, |
| "vision_center_crop_size": null, |
| "vision_do_normalize": false, |
| "vision_do_rescale": true, |
| "vision_image_mean": null, |
| "vision_image_std": null, |
| "vision_interpolation": "bilinear", |
| "vision_processor_name": null, |
| "vision_processor_type": "custom", |
| "vision_resize_size": null, |
| "vocab_size": 128008, |
| "words_splitter_type": "whitespace" |
| } |
|
|
