sembr2023-bert-tiny / config.json
admko's picture
End of training
0b26412
{
"_name_or_path": "prajjwal1/bert-tiny",
"architectures": [
"BertForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 128,
"id2label": {
"0": "off",
"1": "space-0",
"2": "space-1",
"3": "space-2",
"4": "space-3",
"5": "nospace-0",
"6": "nospace-1",
"7": "nospace-2",
"8": "nospace-3"
},
"initializer_range": 0.02,
"intermediate_size": 512,
"label2id": {
"nospace-0": 5,
"nospace-1": 6,
"nospace-2": 7,
"nospace-3": 8,
"off": 0,
"space-0": 1,
"space-1": 2,
"space-2": 3,
"space-3": 4
},
"layer_norm_eps": 1e-12,
"max_indent": 3,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 2,
"num_hidden_layers": 2,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"torch_dtype": "float32",
"transformers_version": "4.34.1",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 30524
}