CoolFace
Modelpublic

LocalDoc/azerbaijani-text-quality-classifier

sourceHugging Faceapache-2.0updated 4mo agoView on Hugging Face
0likes9downloads
config.json86 linesDownload Raw Back to root
1{2  "architectures": [3    "ModernBertForSequenceClassification"4  ],5  "attention_bias": false,6  "attention_dropout": 0.0,7  "bos_token_id": 2,8  "classifier_activation": "gelu",9  "classifier_bias": false,10  "classifier_dropout": 0.0,11  "classifier_pooling": "mean",12  "cls_token_id": 1,13  "decoder_bias": true,14  "deterministic_flash_attn": false,15  "dtype": "bfloat16",16  "embedding_dropout": 0.0,17  "eos_token_id": 1,18  "global_attn_every_n_layers": 3,19  "gradient_checkpointing": false,20  "hidden_activation": "gelu",21  "hidden_size": 768,22  "id2label": {23    "0": "LABEL_0"24  },25  "initializer_cutoff_factor": 2.0,26  "initializer_range": 0.02,27  "intermediate_size": 1152,28  "label2id": {29    "LABEL_0": 030  },31  "layer_norm_eps": 1e-05,32  "layer_types": [33    "full_attention",34    "sliding_attention",35    "sliding_attention",36    "full_attention",37    "sliding_attention",38    "sliding_attention",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  ],56  "local_attention": 128,57  "mask_token_id": 4,58  "max_position_embeddings": 8192,59  "mlp_bias": false,60  "mlp_dropout": 0.0,61  "model_type": "modernbert",62  "norm_bias": false,63  "norm_eps": 1e-05,64  "num_attention_heads": 12,65  "num_hidden_layers": 22,66  "pad_token_id": 0,67  "position_embedding_type": "sans_pos",68  "problem_type": "regression",69  "rope_parameters": {70    "full_attention": {71      "rope_theta": 160000,72      "rope_type": "default"73    },74    "sliding_attention": {75      "rope_theta": 160000,76      "rope_type": "default"77    }78  },79  "sep_token_id": 1,80  "sparse_pred_ignore_index": -100,81  "sparse_prediction": false,82  "tie_word_embeddings": true,83  "transformers_version": "5.9.0",84  "vocab_size": 25600085}86