| { | |
| "architectures": [ | |
| "MoEBertModel" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "auto_map": { | |
| "AutoConfig": "configuration_bert_moe.MoeBertConfig", | |
| "AutoModel": "modeling_bert_hash.MoeBertModel" | |
| }, | |
| "classifier_dropout": null, | |
| "dtype": "float32", | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 128, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 128, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert_moe", | |
| "moebert_expert_dim": 128, | |
| "moebert_expert_dropout": 0.1, | |
| "moebert_expert_num": 16, | |
| "moebert_load_importance": null, | |
| "moebert_route_hash_list": null, | |
| "moebert_route_method": "gate-token", | |
| "moebert_share_importance": 0.5, | |
| "num_attention_heads": 2, | |
| "num_hidden_layers": 2, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "transformers_version": "4.57.3", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 30522 | |
| } | |