|
{ |
|
"architectures": [ |
|
"StructformerModel", |
|
"StructformerModelForSequenceClassification" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"auto_map": { |
|
"AutoConfig": "structformer_as_hf_no_parser.StructformerConfig", |
|
"AutoModelForMaskedLM": "structformer_as_hf_no_parser.StructformerModel", |
|
"AutoModelForSequenceClassification": "structformer_as_hf_no_parser.StructformerModelForSequenceClassification" |
|
}, |
|
|
|
"conv_size": 9, |
|
"dropatt": 0.1, |
|
"dropout": 0.1, |
|
"hidden_size": 768, |
|
"model_type": "structformer", |
|
"n_context_layers": 0, |
|
"n_parser_layers": 0, |
|
"nhead": 12, |
|
"nlayers": 12, |
|
"ntokens": 32000, |
|
"pad": 0, |
|
"pos_emb": true, |
|
"relations": [ |
|
"head", |
|
"child" |
|
], |
|
"relative_bias": false, |
|
"torch_dtype": "float32", |
|
"transformers_version": "4.18.0", |
|
"weight_act": "softmax", |
|
|
|
|
|
"bos_token_id": 0, |
|
"classifier_dropout": null, |
|
|
|
"eos_token_id": 2, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"layer_norm_eps": 1e-05, |
|
"max_position_embeddings": 514, |
|
|
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 12, |
|
"pad_token_id": 1, |
|
"position_embedding_type": "absolute", |
|
|
|
"type_vocab_size": 1, |
|
"use_cache": true, |
|
"vocab_size": 32000 |
|
|
|
} |