blepine/modernFinBERTLarge2
05
1{2 "_name_or_path": "blepine/modernFinBERTLarge",3 "architectures": [4 "ModernBertForMaskedLM"5 ],6 "attention_bias": false,7 "attention_dropout": 0.0,8 "attention_probs_dropout_prob": 0.1,9 "bos_token_id": 50281,10 "classifier_activation": "gelu",11 "classifier_bias": false,12 "classifier_dropout": 0.0,13 "classifier_pooling": "mean",14 "cls_token_id": 50281,15 "decoder_bias": true,16 "deterministic_flash_attn": false,17 "embedding_dropout": 0.0,18 "eos_token_id": 50282,19 "global_attn_every_n_layers": 3,20 "global_rope_theta": 160000.0,21 "gradient_checkpointing": false,22 "hidden_activation": "gelu",23 "hidden_dropout_prob": 0.15,24 "hidden_size": 1024,25 "initializer_cutoff_factor": 2.0,26 "initializer_range": 0.02,27 "intermediate_size": 2624,28 "layer_norm_eps": 1e-05,29 "local_attention": 128,30 "local_rope_theta": 10000.0,31 "max_position_embeddings": 8192,32 "mlp_bias": false,33 "mlp_dropout": 0.0,34 "model_type": "modernbert",35 "norm_bias": false,36 "norm_eps": 1e-05,37 "num_attention_heads": 16,38 "num_hidden_layers": 28,39 "pad_token_id": 50283,40 "position_embedding_type": "absolute",41 "reference_compile": true,42 "sep_token_id": 50282,43 "sparse_pred_ignore_index": -100,44 "sparse_prediction": false,45 "torch_dtype": "float32",46 "transformers_version": "4.48.0.dev0",47 "vocab_size": 5036848}49 