Publish ModernBERT-CNN with concise usage, training details and own evaluation metrics
90316bb verified | { | |
| "architectures": [ | |
| "VisualRelatednessModel" | |
| ], | |
| "model_type": "modernbert-cnn-relatedness", | |
| "bert_config": { | |
| "pad_token_id": 50283, | |
| "bos_token_id": 50281, | |
| "eos_token_id": 50282, | |
| "cls_token_id": 50281, | |
| "sep_token_id": 50282, | |
| "tie_word_embeddings": true, | |
| "vocab_size": 50368, | |
| "max_position_embeddings": 8192, | |
| "hidden_size": 768, | |
| "intermediate_size": 1152, | |
| "num_hidden_layers": 22, | |
| "num_attention_heads": 12, | |
| "initializer_range": 0.02, | |
| "initializer_cutoff_factor": 2.0, | |
| "norm_eps": 1e-05, | |
| "norm_bias": false, | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "hidden_activation": "gelu", | |
| "local_attention": 128, | |
| "embedding_dropout": 0.0, | |
| "mlp_bias": false, | |
| "mlp_dropout": 0.0, | |
| "decoder_bias": true, | |
| "classifier_pooling": "mean", | |
| "classifier_dropout": 0.0, | |
| "classifier_bias": false, | |
| "classifier_activation": "gelu", | |
| "deterministic_flash_attn": false, | |
| "sparse_prediction": false, | |
| "sparse_pred_ignore_index": -100, | |
| "layer_types": [ | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention" | |
| ], | |
| "global_attn_every_n_layers": 3, | |
| "rope_parameters": { | |
| "sliding_attention": { | |
| "rope_type": "default", | |
| "rope_theta": 10000.0 | |
| }, | |
| "full_attention": { | |
| "rope_type": "default", | |
| "rope_theta": 160000.0 | |
| } | |
| }, | |
| "return_dict": true, | |
| "output_hidden_states": false, | |
| "dtype": "float32", | |
| "chunk_size_feed_forward": 0, | |
| "is_encoder_decoder": false, | |
| "architectures": [ | |
| "ModernBertForMaskedLM" | |
| ], | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "problem_type": null, | |
| "_name_or_path": "answerdotai/ModernBERT-base", | |
| "transformers_version": "5.3.0", | |
| "gradient_checkpointing": false, | |
| "layer_norm_eps": 1e-05, | |
| "model_type": "modernbert", | |
| "position_embedding_type": "absolute", | |
| "output_attentions": false | |
| }, | |
| "model_options": { | |
| "architecture": "modernbert-cnn", | |
| "seq_len": 64, | |
| "cnn_filters": 32, | |
| "cnn_kernel_size": 3, | |
| "num_bert_layers": 22, | |
| "tune_embeddings": false | |
| }, | |
| "best_validation_loss": 0.2562806813490731 | |
| } | |