| { |
| "architectures": [ |
| "ModernBertForSequenceClassification" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 2, |
| "classifier_activation": "gelu", |
| "classifier_bias": false, |
| "classifier_dropout": 0.0, |
| "classifier_pooling": "mean", |
| "cls_token_id": 1, |
| "decoder_bias": true, |
| "deterministic_flash_attn": false, |
| "dtype": "float32", |
| "embedding_dropout": 0.0, |
| "eos_token_id": 1, |
| "global_attn_every_n_layers": 3, |
| "gradient_checkpointing": false, |
| "hidden_activation": "gelu", |
| "hidden_size": 768, |
| "id2label": { |
| "0": "task_open_qa", |
| "1": "task_closed_qa", |
| "2": "task_summarization", |
| "3": "task_text_generation", |
| "4": "task_code_generation", |
| "5": "task_chatbot", |
| "6": "task_classification", |
| "7": "task_rewrite", |
| "8": "task_brainstorming", |
| "9": "task_extraction", |
| "10": "task_other", |
| "11": "creativity", |
| "12": "reasoning", |
| "13": "contextual_knowledge", |
| "14": "domain_knowledge", |
| "15": "constraints", |
| "16": "complexity" |
| }, |
| "initializer_cutoff_factor": 2.0, |
| "initializer_range": 0.02, |
| "intermediate_size": 1152, |
| "label2id": { |
| "complexity": 16, |
| "constraints": 15, |
| "contextual_knowledge": 13, |
| "creativity": 11, |
| "domain_knowledge": 14, |
| "reasoning": 12, |
| "task_brainstorming": 8, |
| "task_chatbot": 5, |
| "task_classification": 6, |
| "task_closed_qa": 1, |
| "task_code_generation": 4, |
| "task_extraction": 9, |
| "task_open_qa": 0, |
| "task_other": 10, |
| "task_rewrite": 7, |
| "task_summarization": 2, |
| "task_text_generation": 3 |
| }, |
| "layer_norm_eps": 1e-05, |
| "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" |
| ], |
| "local_attention": 128, |
| "mask_token_id": 4, |
| "max_position_embeddings": 8192, |
| "mlp_bias": false, |
| "mlp_dropout": 0.0, |
| "model_type": "modernbert", |
| "norm_bias": false, |
| "norm_eps": 1e-05, |
| "num_attention_heads": 12, |
| "num_hidden_layers": 22, |
| "pad_token_id": 0, |
| "position_embedding_type": "sans_pos", |
| "problem_type": "multi_label_classification", |
| "rope_parameters": { |
| "full_attention": { |
| "rope_theta": 160000, |
| "rope_type": "default" |
| }, |
| "sliding_attention": { |
| "rope_theta": 160000, |
| "rope_type": "default" |
| } |
| }, |
| "sep_token_id": 1, |
| "sparse_pred_ignore_index": -100, |
| "sparse_prediction": false, |
| "tie_word_embeddings": true, |
| "transformers_version": "5.17.0", |
| "uses_context": false, |
| "vocab_size": 256000 |
| } |
|
|
