{ "add_cross_attention": false, "architectures": [ "RnaBertForPreTraining" ], "attention_dropout": 0.0, "bos_token_id": 1, "dtype": "float32", "eos_token_id": 2, "head": null, "hidden_act": "gelu", "hidden_dropout": 0.0, "hidden_size": 120, "id2label": { "0": "LABEL_0" }, "initializer_range": 0.02, "intermediate_size": 40, "is_decoder": false, "label2id": { "LABEL_0": 0 }, "layer_norm_eps": 1e-12, "lm_head": null, "mask_token_id": 4, "max_position_embeddings": 440, "model_type": "rnabert", "null_token_id": 5, "num_attention_heads": 12, "num_hidden_layers": 6, "pad_token_id": 0, "position_embedding_type": "absolute", "ss_vocab_size": 8, "transformers_version": "5.0.0", "type_vocab_size": 2, "unk_token_id": 3, "use_cache": true, "vocab_size": 26 }