cointegrated/rubert-tiny

1{2  "_name_or_path": "cointegrated/rubert-tiny",3  "architectures": [4    "BertForPreTraining"5  ],6  "attention_probs_dropout_prob": 0.1,7  "emb_size": 312,8  "gradient_checkpointing": false,9  "hidden_act": "gelu",10  "hidden_dropout_prob": 0.1,11  "hidden_size": 312,12  "initializer_range": 0.02,13  "intermediate_size": 600,14  "layer_norm_eps": 1e-12,15  "max_position_embeddings": 512,16  "model_type": "bert",17  "num_attention_heads": 12,18  "num_hidden_layers": 3,19  "pad_token_id": 0,20  "position_embedding_type": "absolute",21  "transformers_version": "4.6.1",22  "type_vocab_size": 2,23  "use_cache": true,24  "vocab_size": 2956425}26