aieng-lab/ModernBERT-large_comment-type-java
024
1{2 "_name_or_path": "answerdotai/ModernBERT-large",3 "architectures": [4 "ModernBertForSequenceClassification"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "bos_token_id": 50281,9 "classifier_activation": "gelu",10 "classifier_bias": false,11 "classifier_dropout": 0.0,12 "classifier_pooling": "mean",13 "cls_token_id": 50281,14 "decoder_bias": true,15 "deterministic_flash_attn": false,16 "embedding_dropout": 0.0,17 "eos_token_id": 50282,18 "global_attn_every_n_layers": 3,19 "global_rope_theta": 160000.0,20 "gradient_checkpointing": false,21 "hidden_activation": "gelu",22 "hidden_size": 1024,23 "id2label": {24 "0": "LABEL_0",25 "1": "LABEL_1",26 "2": "LABEL_2",27 "3": "LABEL_3",28 "4": "LABEL_4",29 "5": "LABEL_5",30 "6": "LABEL_6"31 },32 "initializer_cutoff_factor": 2.0,33 "initializer_range": 0.02,34 "intermediate_size": 2624,35 "label2id": {36 "LABEL_0": 0,37 "LABEL_1": 1,38 "LABEL_2": 2,39 "LABEL_3": 3,40 "LABEL_4": 4,41 "LABEL_5": 5,42 "LABEL_6": 643 },44 "layer_norm_eps": 1e-05,45 "local_attention": 128,46 "local_rope_theta": 10000.0,47 "max_position_embeddings": 8192,48 "mlp_bias": false,49 "mlp_dropout": 0.0,50 "model_type": "modernbert",51 "norm_bias": false,52 "norm_eps": 1e-05,53 "num_attention_heads": 16,54 "num_hidden_layers": 28,55 "pad_token_id": 50283,56 "position_embedding_type": "absolute",57 "problem_type": "multi_label_classification",58 "reference_compile": true,59 "repad_logits_with_grad": false,60 "sep_token_id": 50282,61 "sparse_pred_ignore_index": -100,62 "sparse_prediction": false,63 "torch_dtype": "bfloat16",64 "transformers_version": "4.48.3",65 "vocab_size": 5036866}67 