kiddothe2b's picture
Update config.json
7c46478
{
"_name_or_path": "kiddothe2b/hierarchical-transformer-I3-mini-1024",
"architectures": [
"HATForMaskedLM"
],
"auto_map": {
"AutoConfig": "configuration_hat.HATConfig",
"AutoTokenizer": "tokenization_hat.HATTokenizer",
"AutoModel": "modelling_hat.HATModel",
"AutoModelForMaskedLM": "modelling_hat.HATForMaskedLM",
"AutoModelForMultipleChoice": "modelling_hat.HATForMultipleChoice",
"AutoModelForQuestionAnswering": "modelling_hat.HATForQuestionAnswering",
"AutoModelForSequenceClassification": "modelling_hat.HATForSequenceClassification",
"AutoModelForTokenClassification": "modelling_hat.HATForTokenClassification"
},
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"encoder_layout": {
"0": {
"document_encoder": false,
"sentence_encoder": true
},
"1": {
"document_encoder": true,
"sentence_encoder": true
},
"2": {
"document_encoder": true,
"sentence_encoder": false
},
"3": {
"document_encoder": false,
"sentence_encoder": true
},
"4": {
"document_encoder": true,
"sentence_encoder": true
},
"5": {
"document_encoder": true,
"sentence_encoder": false
},
"6": {
"document_encoder": false,
"sentence_encoder": true
},
"7": {
"document_encoder": true,
"sentence_encoder": true
},
"8": {
"document_encoder": true,
"sentence_encoder": false
}
},
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 256,
"initializer_range": 0.02,
"intermediate_size": 1024,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 128,
"max_sentence_length": 128,
"max_sentence_size": 128,
"max_sentences": 8,
"model_max_length": 1024,
"model_type": "hierarchical-transformer",
"num_attention_heads": 4,
"num_hidden_layers": 9,
"output_past": true,
"pad_token_id": 0,
"parameters": 136350720,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.19.0.dev0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30522
}