{ "_name_or_path": "albert-base-v2", "architectures": [ "AlbertForTokenClassification" ], "attention_probs_dropout_prob": 0, "bos_token_id": 2, "classifier_dropout_prob": 0.1, "down_scale_factor": 1, "embedding_size": 128, "eos_token_id": 3, "gap_size": 0, "hidden_act": "gelu_new", "hidden_dropout_prob": 0, "hidden_size": 768, "id2label": { "0": "O", "1": "B-PER", "2": "I-PER", "3": "B-ORG", "4": "I-ORG", "5": "B-LOC", "6": "I-LOC", "7": "B-MISC", "8": "I-MISC" }, "initializer_range": 0.02, "inner_group_num": 1, "intermediate_size": 3072, "label2id": { "O": 0, "B-PER": 1, "I-PER": 2, "B-ORG": 3, "I-ORG": 4, "B-LOC": 5, "I-LOC": 6, "B-MISC": 7, "I-MISC": 8 }, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "albert", "net_structure_type": 0, "num_attention_heads": 12, "num_hidden_groups": 1, "num_hidden_layers": 12, "num_memory_blocks": 0, "pad_token_id": 0, "position_embedding_type": "absolute", "torch_dtype": "float32", "transformers_version": "4.16.2", "type_vocab_size": 2, "vocab_size": 30000 }