WpythonW/RUbert-tiny_custom_test

1{2  "_name_or_path": "cointegrated/rubert-tiny2",3  "architectures": [4    "BertModel"5  ],6  "attention_probs_dropout_prob": 0.1,7  "classifier_dropout": null,8  "emb_size": 312,9  "gradient_checkpointing": false,10  "hidden_act": "gelu",11  "hidden_dropout_prob": 0.1,12  "hidden_size": 312,13  "initializer_range": 0.02,14  "intermediate_size": 600,15  "layer_norm_eps": 1e-12,16  "max_position_embeddings": 2048,17  "model_type": "bert",18  "num_attention_heads": 12,19  "num_hidden_layers": 3,20  "pad_token_id": 0,21  "position_embedding_type": "absolute",22  "torch_dtype": "float32",23  "transformers_version": "4.44.0",24  "type_vocab_size": 2,25  "use_cache": true,26  "vocab_size": 8382827}28