Rami/multi-label-class-classification-on-github-issues

1{2  "_name_or_path": "neuralmagic/oBERT-12-upstream-pruned-unstructured-97",3  "architectures": [4    "BertForSequenceClassification"5  ],6  "attention_probs_dropout_prob": 0.1,7  "classifier_dropout": null,8  "gradient_checkpointing": false,9  "hidden_act": "gelu",10  "hidden_dropout_prob": 0.1,11  "hidden_size": 768,12  "id2label": {13    "0": "3rd party",14    "1": "accelerator: tpu",15    "2": "breaking change",16    "3": "bug",17    "4": "callback",18    "5": "callback: model checkpoint",19    "6": "checkpointing",20    "7": "ci",21    "8": "code quality",22    "9": "data handling",23    "10": "design",24    "11": "discussion",25    "12": "distributed",26    "13": "docs",27    "14": "duplicate",28    "15": "environment",29    "16": "environment: slurm",30    "17": "example",31    "18": "fault tolerance",32    "19": "feature",33    "20": "good first issue",34    "21": "help wanted",35    "22": "hooks",36    "23": "let's do it!",37    "24": "logger",38    "25": "logger: mlflow",39    "26": "logger: wandb",40    "27": "logging",41    "28": "loops",42    "29": "lr scheduler",43    "30": "optimizer",44    "31": "priority: 0",45    "32": "priority: 1",46    "33": "priority: 2",47    "34": "question",48    "35": "ready",49    "36": "refactor",50    "37": "strategy: ddp",51    "38": "strategy: dp",52    "39": "trainer: test",53    "40": "trainer: tune",54    "41": "trainer: validate",55    "42": "waiting on author",56    "43": "won't fix",57    "44": "working as intended"58  },59  "initializer_range": 0.02,60  "intermediate_size": 3072,61  "label2id": {62    "3rd party": 0,63    "accelerator: tpu": 1,64    "breaking change": 2,65    "bug": 3,66    "callback": 4,67    "callback: model checkpoint": 5,68    "checkpointing": 6,69    "ci": 7,70    "code quality": 8,71    "data handling": 9,72    "design": 10,73    "discussion": 11,74    "distributed": 12,75    "docs": 13,76    "duplicate": 14,77    "environment": 15,78    "environment: slurm": 16,79    "example": 17,80    "fault tolerance": 18,81    "feature": 19,82    "good first issue": 20,83    "help wanted": 21,84    "hooks": 22,85    "let's do it!": 23,86    "logger": 24,87    "logger: mlflow": 25,88    "logger: wandb": 26,89    "logging": 27,90    "loops": 28,91    "lr scheduler": 29,92    "optimizer": 30,93    "priority: 0": 31,94    "priority: 1": 32,95    "priority: 2": 33,96    "question": 34,97    "ready": 35,98    "refactor": 36,99    "strategy: ddp": 37,100    "strategy: dp": 38,101    "trainer: test": 39,102    "trainer: tune": 40,103    "trainer: validate": 41,104    "waiting on author": 42,105    "won't fix": 43,106    "working as intended": 44107  },108  "layer_norm_eps": 1e-12,109  "max_position_embeddings": 512,110  "model_type": "bert",111  "num_attention_heads": 12,112  "num_hidden_layers": 12,113  "pad_token_id": 0,114  "position_embedding_type": "absolute",115  "problem_type": "multi_label_classification",116  "torch_dtype": "float32",117  "transformers_version": "4.25.1",118  "type_vocab_size": 2,119  "use_cache": true,120  "vocab_size": 30522121}122