| { | |
| "architectures": [ | |
| "LtgBertForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 384, | |
| "intermediate_size": 1024, | |
| "layer_norm_eps": 1e-07, | |
| "mask_token_id": 4, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 6, | |
| "num_hidden_layers": 12, | |
| "output_all_encoded_layers": true, | |
| "pad_token_id": 3, | |
| "position_bucket_size": 32, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.44.2", | |
| "vocab_size": 6144 | |
| } | |