CoolFace
Modelpublic

addyo07/query-scope-classifier

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face
0likes
config.json92 linesDownload Raw Back to onnx
1{2  "architectures": [3    "ModernBertForSequenceClassification"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": null,8  "classifier_activation": "gelu",9  "classifier_bias": false,10  "classifier_dropout": 0.0,11  "classifier_pooling": "mean",12  "cls_token_id": 50281,13  "decoder_bias": true,14  "deterministic_flash_attn": false,15  "dtype": "float32",16  "embedding_dropout": 0.0,17  "eos_token_id": null,18  "global_attn_every_n_layers": 3,19  "gradient_checkpointing": false,20  "hidden_activation": "gelu",21  "hidden_size": 768,22  "id2label": {23    "0": "ChitChat",24    "1": "User",25    "2": "Domain",26    "3": "Temporal"27  },28  "initializer_cutoff_factor": 2.0,29  "initializer_range": 0.02,30  "intermediate_size": 1152,31  "label2id": {32    "ChitChat": 0,33    "Domain": 2,34    "Temporal": 3,35    "User": 136  },37  "layer_norm_eps": 1e-05,38  "layer_types": [39    "full_attention",40    "sliding_attention",41    "sliding_attention",42    "full_attention",43    "sliding_attention",44    "sliding_attention",45    "full_attention",46    "sliding_attention",47    "sliding_attention",48    "full_attention",49    "sliding_attention",50    "sliding_attention",51    "full_attention",52    "sliding_attention",53    "sliding_attention",54    "full_attention",55    "sliding_attention",56    "sliding_attention",57    "full_attention",58    "sliding_attention",59    "sliding_attention",60    "full_attention"61  ],62  "local_attention": 128,63  "max_position_embeddings": 8192,64  "mlp_bias": false,65  "mlp_dropout": 0.0,66  "model_type": "modernbert",67  "norm_bias": false,68  "norm_eps": 1e-05,69  "num_attention_heads": 12,70  "num_hidden_layers": 22,71  "pad_token_id": 50283,72  "position_embedding_type": "absolute",73  "problem_type": "single_label_classification",74  "rope_parameters": {75    "full_attention": {76      "rope_theta": 160000.0,77      "rope_type": "default"78    },79    "sliding_attention": {80      "rope_theta": 10000.0,81      "rope_type": "default"82    }83  },84  "sep_token_id": 50282,85  "sparse_pred_ignore_index": -100,86  "sparse_prediction": false,87  "tie_word_embeddings": true,88  "transformers_version": "5.14.1",89  "use_cache": false,90  "vocab_size": 5036891}92