| { | |
| "architectures": [ | |
| "RoPEBertForMaskedLM" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "modeling_rope_bert.RoPEBertConfig", | |
| "AutoModel": "modeling_rope_bert.RoPEBertModel", | |
| "AutoModelForMaskedLM": "modeling_rope_bert.RoPEBertForMaskedLM", | |
| "AutoModelForSequenceClassification": "modeling_rope_bert.RoPEBertForSequenceClassification" | |
| }, | |
| "attention_probs_dropout_prob": 0.1, | |
| "attn_implementation": "eager", | |
| "classifier_dropout": null, | |
| "directionality": "bidi", | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "pad_token_id": 0, | |
| "pooler_type": "mean", | |
| "rope_scaling": null, | |
| "rope_theta": 10000.0, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.37.2", | |
| "type_vocab_size": 2, | |
| "vocab_size": 120138 | |
| } | |