bert128b128l / config.json
IvashinMaxim's picture
End of training
fada834 verified
raw
history blame contribute delete
981 Bytes
{
"_name_or_path": "cointegrated/rubert-tiny2",
"architectures": [
"BertForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"emb_size": 312,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 312,
"id2label": {
"0": "Gogol",
"1": "Dostoevsky",
"2": "Chekhov",
"3": "Gorky",
"4": "Tolstoy"
},
"initializer_range": 0.02,
"intermediate_size": 600,
"label2id": {
"Chekhov": 2,
"Dostoevsky": 1,
"Gogol": 0,
"Gorky": 3,
"Tolstoy": 4
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 2048,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 3,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"problem_type": "single_label_classification",
"torch_dtype": "float32",
"transformers_version": "4.41.0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 83828
}