MST-MIXER/config/avsd_bart_large.json

116 lines
2.9 KiB
JSON
Raw Normal View History

2024-07-08 11:41:28 +02:00
{
"activation_dropout": 0.1,
"activation_function": "gelu",
"add_bias_logits": false,
"add_final_layer_norm": false,
"architectures": [
"BartModel"
],
"attention_dropout": 0.1,
"bos_token_id": 0,
"classif_dropout": 0.1,
"classifier_dropout": 0.0,
"d_model": 1024,
"decoder_attention_heads": 16,
"decoder_ffn_dim": 4096,
"decoder_layerdrop": 0.0,
"decoder_layers": 12,
"decoder_start_token_id": 2,
"dropout": 0.1,
"early_stopping": true,
"encoder_attention_heads": 16,
"encoder_ffn_dim": 4096,
"encoder_layerdrop": 0.0,
"encoder_layers": 12,
"eos_token_id": 2,
"forced_eos_token_id": 2,
"forced_bos_token_id": 0,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"max_position_embeddings": 1024,
"model_type": "bart",
"no_repeat_ngram_size": 3,
"normalize_before": false,
"num_beams": 4,
"num_hidden_layers": 12,
"pad_token_id": 1,
"scale_embedding": false,
"task_specific_params": {
"summarization": {
"length_penalty": 1.0,
"max_length": 128,
"min_length": 12,
"num_beams": 4
},
"summarization_cnn": {
"length_penalty": 2.0,
"max_length": 142,
"min_length": 56,
"num_beams": 4
},
"summarization_xsum": {
"length_penalty": 1.0,
"max_length": 62,
"min_length": 11,
"num_beams": 6
}
},
"transformers_version": "4.7.0.dev0",
"use_cache": true,
"vocab_size": 50265,
"d_i3d_flow": 2048,
"d_i3d_rgb": 2048,
"d_sam": 512,
"d_audio": 128,
"top_k": 10,
"num_nn": 4,
"gnn_type": "appnp",
"use_random_graphs": false,
"integrate_all_gnn_features": true,
"use_elbo_local": true,
"use_elbo_global": true,
"use_non_linear": true,
"gnn_K": 2,
"gnn_alpha": 0.1,
"num_modalities": 6,
"local_gnn_d_hidden": 1024,
"global_gnn_d_hidden": 1024,
"num_local_gnn_heads": 2,
"num_global_gnn_heads": 4,
"local_gnn_dropout": 0.1,
"global_gnn_dropout": 0.1,
"local_fc_dropout": 0.1,
"global_fc_dropout": 0.1,
"num_local_gnn_layers": 1,
"num_global_gnn_layers": 1,
"num_local_fc_layers": 1,
"num_global_fc_layers": 1,
"use_local_gnn_bn": true,
"use_global_gnn_bn": true,
"use_local_fc_bn": true,
"use_global_fc_bn": true,
"local_gnn_concat": true,
"global_gnn_concat": true,
"num_local_gr_learner_heads": 8,
"num_global_gr_learner_heads": 8,
"init_adj_ratio": 0.5,
"adj_ratio": 0.5,
"alpha": 0.9,
"gnns_every": 4,
"num_layers_state_fc_decoder": 2,
"dropout_state_fc_decoder": 0.3
}