| { | |
| "adapter_reduction": 16, | |
| "architectures": [ | |
| "ModernAlbertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "embedding_size": 128, | |
| "group_depth": 8, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 1024, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 8192, | |
| "model_type": "ModernALBERT", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 24, | |
| "output_hidden_states": true, | |
| "pad_token_id": 0, | |
| "problem_type": "single_label_classification", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.55.0", | |
| "use_adapter": true, | |
| "use_cache": true, | |
| "vocab_size": 50368 | |
| } | |