{ "_name_or_path": "/home/haowei/haowei/continual-post-training/agnews_unsup_roberta", "adapter_mode": "parallel", "adapter_task": 5, "adapters": { "adapters": {}, "config_map": {}, "fusion_config_map": {}, "fusions": {} }, "architectures": [ "RobertaMaskForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "attn_adapter_size": 512, "bos_token_id": 0, "classifier_dropout": null, "eos_token_id": 2, "ffn_adapter_size": 768, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-05, "max_position_embeddings": 514, "model_type": "roberta", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 1, "position_embedding_type": "absolute", "smax": 400, "torch_dtype": "float32", "transformers_version": "4.11.3", "type_vocab_size": 1, "use_cache": true, "vocab_size": 50265 }