ltg/norbert3-base
7964
1{2 "architectures": [3 "NorbertForMaskedLM"4 ],5 "auto_map": {6 "AutoConfig": "configuration_norbert.NorbertConfig",7 "AutoModel": "modeling_norbert.NorbertModel",8 "AutoModelForMaskedLM": "modeling_norbert.NorbertForMaskedLM",9 "AutoModelForSequenceClassification": "modeling_norbert.NorbertForSequenceClassification",10 "AutoModelForTokenClassification": "modeling_norbert.NorbertForTokenClassification",11 "AutoModelForQuestionAnswering": "modeling_norbert.NorbertForQuestionAnswering",12 "AutoModelForMultipleChoice": "modeling_norbert.NorbertForMultipleChoice"13 },14 "attention_probs_dropout_prob": 0.1,15 "hidden_dropout_prob": 0.1,16 "hidden_size": 768,17 "intermediate_size": 2048,18 "layer_norm_eps": 1e-07,19 "max_position_embeddings": 512,20 "num_attention_heads": 12,21 "num_hidden_layers": 12,22 "position_bucket_size": 32,23 "torch_dtype": "float32",24 "transformers_version": "4.23.1",25 "vocab_size": 5000026}27 