codeparrot/unixcoder-java-complexity-prediction

1{2  "_name_or_path": "microsoft/unixcoder-base-nine",3  "architectures": [4    "RobertaForSequenceClassification"5  ],6  "attention_probs_dropout_prob": 0.1,7  "bos_token_id": 0,8  "classifier_dropout": null,9  "eos_token_id": 2,10  "gradient_checkpointing": false,11  "hidden_act": "gelu",12  "hidden_dropout_prob": 0.1,13  "hidden_size": 768,14  "id2label": {15    "0": "LABEL_0",16    "1": "LABEL_1",17    "2": "LABEL_2",18    "3": "LABEL_3",19    "4": "LABEL_4",20    "5": "LABEL_5",21    "6": "LABEL_6"22  },23  "initializer_range": 0.02,24  "intermediate_size": 3072,25  "label2id": {26    "LABEL_0": 0,27    "LABEL_1": 1,28    "LABEL_2": 2,29    "LABEL_3": 3,30    "LABEL_4": 4,31    "LABEL_5": 5,32    "LABEL_6": 633  },34  "layer_norm_eps": 1e-05,35  "max_position_embeddings": 1026,36  "model_type": "roberta",37  "num_attention_heads": 12,38  "num_hidden_layers": 12,39  "output_past": true,40  "pad_token_id": 2,41  "position_embedding_type": "absolute",42  "problem_type": "single_label_classification",43  "torch_dtype": "float32",44  "transformers_version": "4.21.1",45  "type_vocab_size": 10,46  "use_cache": true,47  "vocab_size": 5141648}49