SSMNspanTagger / config.json
in6087
add model
e919953
raw
history blame
1.3 kB
{
"_name_or_path": "/tmp/test-richard_bert_base_uncased",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"directionality": "bidi",
"finetuning_task": "ner",
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "AFTER_COMPLEX_NP",
"1": "BEFORE_COMPLEX_NP",
"2": "ERROR",
"3": "IN_COMPLEX_NP",
"4": "IN_COMPLEX_NP_AFTERSIGN",
"5": "IN_COMPLEX_NP_BEFORESIGN",
"6": "UNKNOWN"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"AFTER_COMPLEX_NP": 0,
"BEFORE_COMPLEX_NP": 1,
"ERROR": 2,
"IN_COMPLEX_NP": 3,
"IN_COMPLEX_NP_AFTERSIGN": 4,
"IN_COMPLEX_NP_BEFORESIGN": 5,
"UNKNOWN": 6
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 16,
"num_hidden_layers": 24,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.9.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 28996
}