Hugging-GK/ModerBert-MultiLabel-StackExchange-stack_exp_imb_exp1
08
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 "global_rope_theta": 160000.0,20 "gradient_checkpointing": false,21 "hidden_activation": "gelu",22 "hidden_size": 768,23 "id2label": {24 "0": "c#",25 "1": "java",26 "2": "php",27 "3": "javascript",28 "4": "android",29 "5": "jquery",30 "6": "c++",31 "7": "python",32 "8": "iphone",33 "9": "asp.net"34 },35 "initializer_cutoff_factor": 2.0,36 "initializer_range": 0.02,37 "intermediate_size": 1152,38 "label2id": {39 "android": 4,40 "asp.net": 9,41 "c#": 0,42 "c++": 6,43 "iphone": 8,44 "java": 1,45 "javascript": 3,46 "jquery": 5,47 "php": 2,48 "python": 749 },50 "layer_norm_eps": 1e-05,51 "local_attention": 128,52 "local_rope_theta": 10000.0,53 "max_position_embeddings": 8192,54 "mlp_bias": false,55 "mlp_dropout": 0.0,56 "model_type": "modernbert",57 "norm_bias": false,58 "norm_eps": 1e-05,59 "num_attention_heads": 12,60 "num_hidden_layers": 22,61 "pad_token_id": 50283,62 "position_embedding_type": "absolute",63 "repad_logits_with_grad": false,64 "sep_token_id": 50282,65 "sparse_pred_ignore_index": -100,66 "sparse_prediction": false,67 "transformers_version": "4.57.0",68 "vocab_size": 5036869}70 