| { |
| "_name_or_path": "neuralmagic/oBERT-12-upstream-pruned-unstructured-97", |
| "architectures": [ |
| "BertForSequenceClassification" |
| ], |
| "attention_probs_dropout_prob": 0.1, |
| "classifier_dropout": null, |
| "gradient_checkpointing": false, |
| "hidden_act": "gelu", |
| "hidden_dropout_prob": 0.1, |
| "hidden_size": 768, |
| "id2label": { |
| "0": "3rd party", |
| "1": "accelerator: tpu", |
| "2": "breaking change", |
| "3": "bug", |
| "4": "callback", |
| "5": "callback: model checkpoint", |
| "6": "checkpointing", |
| "7": "ci", |
| "8": "code quality", |
| "9": "data handling", |
| "10": "design", |
| "11": "discussion", |
| "12": "distributed", |
| "13": "docs", |
| "14": "duplicate", |
| "15": "environment", |
| "16": "environment: slurm", |
| "17": "example", |
| "18": "fault tolerance", |
| "19": "feature", |
| "20": "good first issue", |
| "21": "help wanted", |
| "22": "hooks", |
| "23": "let's do it!", |
| "24": "logger", |
| "25": "logger: mlflow", |
| "26": "logger: wandb", |
| "27": "logging", |
| "28": "loops", |
| "29": "lr scheduler", |
| "30": "optimizer", |
| "31": "priority: 0", |
| "32": "priority: 1", |
| "33": "priority: 2", |
| "34": "question", |
| "35": "ready", |
| "36": "refactor", |
| "37": "strategy: ddp", |
| "38": "strategy: dp", |
| "39": "trainer: test", |
| "40": "trainer: tune", |
| "41": "trainer: validate", |
| "42": "waiting on author", |
| "43": "won't fix", |
| "44": "working as intended" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "label2id": { |
| "3rd party": 0, |
| "accelerator: tpu": 1, |
| "breaking change": 2, |
| "bug": 3, |
| "callback": 4, |
| "callback: model checkpoint": 5, |
| "checkpointing": 6, |
| "ci": 7, |
| "code quality": 8, |
| "data handling": 9, |
| "design": 10, |
| "discussion": 11, |
| "distributed": 12, |
| "docs": 13, |
| "duplicate": 14, |
| "environment": 15, |
| "environment: slurm": 16, |
| "example": 17, |
| "fault tolerance": 18, |
| "feature": 19, |
| "good first issue": 20, |
| "help wanted": 21, |
| "hooks": 22, |
| "let's do it!": 23, |
| "logger": 24, |
| "logger: mlflow": 25, |
| "logger: wandb": 26, |
| "logging": 27, |
| "loops": 28, |
| "lr scheduler": 29, |
| "optimizer": 30, |
| "priority: 0": 31, |
| "priority: 1": 32, |
| "priority: 2": 33, |
| "question": 34, |
| "ready": 35, |
| "refactor": 36, |
| "strategy: ddp": 37, |
| "strategy: dp": 38, |
| "trainer: test": 39, |
| "trainer: tune": 40, |
| "trainer: validate": 41, |
| "waiting on author": 42, |
| "won't fix": 43, |
| "working as intended": 44 |
| }, |
| "layer_norm_eps": 1e-12, |
| "max_position_embeddings": 512, |
| "model_type": "bert", |
| "num_attention_heads": 12, |
| "num_hidden_layers": 12, |
| "pad_token_id": 0, |
| "position_embedding_type": "absolute", |
| "problem_type": "multi_label_classification", |
| "torch_dtype": "float32", |
| "transformers_version": "4.25.1", |
| "type_vocab_size": 2, |
| "use_cache": true, |
| "vocab_size": 30522 |
| } |
|
|
