| {"architectures": [ | |
| "MegatronBertForSequenceClassification" | |
| ], | |
| "_num_labels": 2, | |
| "id2label":{"1":"similar","0":"not similar"}, | |
| "vocab_size": 21248, | |
| "hidden_size": 2048, | |
| "num_hidden_layers": 24, | |
| "num_attention_heads": 8, | |
| "hidden_act": "gelu_new", | |
| "intermediate_size": 8192, | |
| "hidden_dropout_prob": 0.1, | |
| "attention_probs_dropout_prob": 0.1, | |
| "max_position_embeddings": 512, | |
| "type_vocab_size": 2, | |
| "initializer_range": 0.2, | |
| "layer_norm_eps": 1e-12, | |
| "gradient_checkpointing": false, | |
| "position_embedding_type": "absolute", | |
| "use_cache": false, | |
| "model_type": "megatron-bert"} | |