| { |
| "add_cross_attention": false, |
| "architectures": [ |
| "XLMRobertaForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "bos_token_id": 0, |
| "classifier_dropout": null, |
| "dtype": "float32", |
| "eos_token_id": 2, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 1024, |
| "id2label": { |
| "0": "LABEL_0" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 4096, |
| "is_decoder": false, |
| "label2id": { |
| "LABEL_0": 0 |
| }, |
| "layer_norm_eps": 1e-05, |
| "max_position_embeddings": 8194, |
| "model_type": "xlm-roberta", |
| "num_attention_heads": 16, |
| "num_hidden_layers": 24, |
| "output_past": true, |
| "pad_token_id": 1, |
| "position_embedding_type": "absolute", |
| "problem_type": "regression", |
| "salience_article_balanced": false, |
| "salience_loss_type": "mse", |
| "salience_multihead_names": [], |
| "salience_score_aggregation": "scalar", |
| "salience_score_semantics": "model_balanced_salience_probability", |
| "salience_score_transform": "identity", |
| "tie_word_embeddings": true, |
| "transformers_version": "5.6.2", |
| "type_vocab_size": 1, |
| "use_cache": false, |
| "vocab_size": 250002 |
| } |
|
|
