CCVspanTagger / config.json
RJ3vans's picture
add model
b10a172
raw
history blame
1.34 kB
{
"_name_or_path": "/tmp/test-richard_bert_base_cased",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"directionality": "bidi",
"finetuning_task": "ner",
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "AFTER_COMPOUND",
"1": "BEFORE_COMPOUND",
"2": "IN_COMPOUND",
"3": "IN_COMPOUND_AFTERSIGN",
"4": "IN_COMPOUND_BEFORESIGN",
"5": "NOT_CLAUSE_COORDINATOR",
"6": "UNKNOWN"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"label2id": {
"AFTER_COMPOUND": 0,
"BEFORE_COMPOUND": 1,
"IN_COMPOUND": 2,
"IN_COMPOUND_AFTERSIGN": 3,
"IN_COMPOUND_BEFORESIGN": 4,
"NOT_CLAUSE_COORDINATOR": 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": "4.20.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 28996
}