shatonix/granite-embedding-math-cs
019
1{2 "architectures": [3 "ModernBertModel"4 ],5 "attention_bias": false,6 "attention_dropout": 0.0,7 "attention_probs_dropout_prob": 0.1,8 "bos_token_id": 50281,9 "classifier_activation": "silu",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 "dtype": "float32",17 "embedding_dropout": 0.0,18 "eos_token_id": 50282,19 "global_attn_every_n_layers": 3,20 "global_rope_theta": 80000.0,21 "gradient_checkpointing": false,22 "hidden_act": "gelu",23 "hidden_activation": "gelu",24 "hidden_dropout_prob": 0.1,25 "hidden_size": 768,26 "initializer_cutoff_factor": 2.0,27 "initializer_range": 0.02,28 "intermediate_size": 1152,29 "layer_norm_eps": 1e-05,30 "local_attention": 128,31 "local_rope_theta": 10000.0,32 "max_position_embeddings": 8192,33 "mlp_bias": false,34 "mlp_dropout": 0.0,35 "model_type": "modernbert",36 "norm_bias": false,37 "norm_eps": 1e-05,38 "num_attention_heads": 12,39 "num_hidden_layers": 22,40 "pad_token_id": 50283,41 "position_embedding_type": "absolute",42 "repad_logits_with_grad": false,43 "sep_token_id": 50282,44 "sparse_pred_ignore_index": -100,45 "sparse_prediction": false,46 "transformers_version": "4.57.3",47 "vocab_size": 5036848}49 