DhimanBose/Bangla_Masked_Language_Model3

1{2  "_name_or_path": "DhimanBose/Bangla_Masked_Language_Model3",3  "architectures": [4    "ElectraForMaskedLM"5  ],6  "attention_probs_dropout_prob": 0.1,7  "classifier_dropout": null,8  "embedding_size": 768,9  "hidden_act": "gelu",10  "hidden_dropout_prob": 0.1,11  "hidden_size": 768,12  "initializer_range": 0.02,13  "intermediate_size": 3072,14  "layer_norm_eps": 1e-12,15  "max_position_embeddings": 512,16  "model_type": "electra",17  "num_attention_heads": 12,18  "num_hidden_layers": 12,19  "pad_token_id": 0,20  "position_embedding_type": "absolute",21  "summary_activation": "gelu",22  "summary_last_dropout": 0.1,23  "summary_type": "first",24  "summary_use_proj": true,25  "torch_dtype": "float32",26  "transformers_version": "4.36.2",27  "type_vocab_size": 2,28  "use_cache": true,29  "vocab_size": 3200030}31