bert-large-NER-rust / config.json
mdizak
Initial
786494d
{
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": null,
"directionality": "bidi",
"do_sample": false,
"eos_token_ids": null,
"finetuning_task": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "O",
"1": "B-MISC",
"2": "I-MISC",
"3": "B-PER",
"4": "I-PER",
"5": "B-ORG",
"6": "I-ORG",
"7": "B-LOC",
"8": "I-LOC"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"is_decoder": false,
"label2id": {
"B-LOC": 7,
"B-MISC": 1,
"B-ORG": 5,
"B-PER": 3,
"I-LOC": 8,
"I-MISC": 2,
"I-ORG": 6,
"I-PER": 4,
"O": 0
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 16,
"num_beams": 1,
"num_hidden_layers": 24,
"num_labels": 9,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_past": true,
"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",
"pruned_heads": {},
"repetition_penalty": 1.0,
"temperature": 1.0,
"top_k": 50,
"top_p": 1.0,
"torchscript": false,
"type_vocab_size": 2,
"use_bfloat16": false,
"vocab_size": 28996
}