SRoBERTa-XL-NER / config.json
Andrija's picture
Init SRoBERTa-XL NER model
3f94e61
raw
history blame
1.16 kB
{
"_name_or_path": "Andrija/SRoBERTa-XL",
"architectures": [
"RobertaForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": 0,
"classifier_dropout": null,
"eos_token_id": 2,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "I-org",
"1": "B-misc",
"2": "B-per",
"3": "B-deriv-per",
"4": "B-org",
"5": "B-loc",
"6": "I-deriv-per",
"7": "I-misc",
"8": "I-loc",
"9": "I-per",
"10": "O"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"I-org": 0,
"B-misc": 1,
"O": 10,
"B-per": 2,
"B-deriv-per": 3,
"B-org": 4,
"B-loc": 5,
"I-deriv-per": 6,
"I-misc": 7,
"I-loc": 8,
"I-per": 9
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 514,
"model_type": "roberta",
"num_attention_heads": 12,
"num_hidden_layers": 6,
"pad_token_id": 1,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.10.3",
"type_vocab_size": 1,
"use_cache": true,
"vocab_size": 48000
}