mlboydaisuke/Granite-Embedding-97M-Multilingual-R2-CoreAI
351
1{2 "architectures": [3 "ModernBertModel"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "bos_token_id": 179934,8 "classifier_activation": "silu",9 "classifier_bias": false,10 "classifier_dropout": 0.0,11 "classifier_pooling": "cls",12 "cls_token_id": 179934,13 "decoder_bias": true,14 "deterministic_flash_attn": false,15 "dtype": "bfloat16",16 "embedding_dropout": 0.0,17 "eos_token_id": 179938,18 "global_attn_every_n_layers": 3,19 "global_rope_theta": 150000.0,20 "gradient_checkpointing": false,21 "hidden_activation": "silu",22 "hidden_size": 384,23 "initializer_cutoff_factor": 2.0,24 "initializer_range": 0.02,25 "intermediate_size": 1536,26 "layer_norm_eps": 1e-05,27 "local_attention": 128,28 "local_rope_theta": 160000.0,29 "max_position_embeddings": 32768,30 "mlp_bias": false,31 "mlp_dropout": 0.0,32 "model_type": "modernbert",33 "norm_bias": false,34 "norm_eps": 1e-05,35 "num_attention_heads": 12,36 "num_hidden_layers": 12,37 "pad_token_id": 179935,38 "position_embedding_type": "absolute",39 "repad_logits_with_grad": false,40 "sep_token_id": 179938,41 "sparse_pred_ignore_index": -100,42 "sparse_prediction": false,43 "transformers_version": "4.56.2",44 "vocab_size": 18000045}46 