aieng-lab/ModernBERT-base_commit-intent
03
1{2 "_name_or_path": "answerdotai/ModernBERT-base",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": 768,23 "id2label": {24 "0": "LABEL_0",25 "1": "LABEL_1",26 "2": "LABEL_2"27 },28 "initializer_cutoff_factor": 2.0,29 "initializer_range": 0.02,30 "intermediate_size": 1152,31 "label2id": {32 "LABEL_0": 0,33 "LABEL_1": 1,34 "LABEL_2": 235 },36 "layer_norm_eps": 1e-05,37 "local_attention": 128,38 "local_rope_theta": 10000.0,39 "max_position_embeddings": 8192,40 "mlp_bias": false,41 "mlp_dropout": 0.0,42 "model_type": "modernbert",43 "norm_bias": false,44 "norm_eps": 1e-05,45 "num_attention_heads": 12,46 "num_hidden_layers": 22,47 "pad_token_id": 50283,48 "position_embedding_type": "absolute",49 "reference_compile": true,50 "repad_logits_with_grad": false,51 "sep_token_id": 50282,52 "sparse_pred_ignore_index": -100,53 "sparse_prediction": false,54 "torch_dtype": "bfloat16",55 "transformers_version": "4.48.3",56 "vocab_size": 5036857}58 