{ "_name_or_path": "kiddothe2b/hierarchical-transformer-base-4096", "architectures": [ "HATForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "auto_map": { "AutoConfig": "configuration_hat.HATConfig", "AutoModel": "modelling_hat.HATModel", "AutoModelForMaskedLM": "modelling_hat.HATForMaskedLM", "AutoModelForMultipleChoice": "modelling_hat.HATForMultipleChoice", "AutoModelForQuestionAnswering": "modelling_hat.HATForQuestionAnswering", "AutoModelForSequenceClassification": "modelling_hat.HATForSequenceClassification", "AutoModelForTokenClassification": "modelling_hat.HATForTokenClassification", "AutoTokenizer": "tokenization_hat.HATTokenizer" }, "bos_token_id": 0, "classifier_dropout": null, "encoder_layout": { "0": { "document_encoder": false, "sentence_encoder": true }, "1": { "document_encoder": false, "sentence_encoder": true }, "10": { "document_encoder": false, "sentence_encoder": true }, "11": { "document_encoder": true, "sentence_encoder": true }, "2": { "document_encoder": true, "sentence_encoder": true }, "3": { "document_encoder": false, "sentence_encoder": true }, "4": { "document_encoder": false, "sentence_encoder": true }, "5": { "document_encoder": true, "sentence_encoder": true }, "6": { "document_encoder": false, "sentence_encoder": true }, "7": { "document_encoder": false, "sentence_encoder": true }, "8": { "document_encoder": true, "sentence_encoder": true }, "9": { "document_encoder": false, "sentence_encoder": true } }, "eos_token_id": 2, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3", "4": "LABEL_4", "5": "LABEL_5", "6": "LABEL_6" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2, "LABEL_3": 3, "LABEL_4": 4, "LABEL_5": 5, "LABEL_6": 6 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 130, "max_sentence_length": 128, "max_sentence_size": 128, "max_sentences": 32, "model_max_length": 4096, "model_type": "hierarchical-transformer", "num_attention_heads": 12, "num_hidden_layers": 12, "output_past": true, "pad_token_id": 1, "parameters": 136350720, "position_embedding_type": "absolute", "problem_type": "single_label_classification", "torch_dtype": "float32", "transformers_version": "4.28.1", "type_vocab_size": 1, "use_cache": true, "vocab_size": 50265 }