| { | |
| "add_linear_bias": true, | |
| "architectures": [ | |
| "RNABertForMaskedLM" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "hidden_act": "swiglu", | |
| "hidden_dropout_prob": 0.0, | |
| "hidden_size": 4352, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 11584, | |
| "layer_norm_eps": 1e-05, | |
| "max_position_embeddings": 4000, | |
| "model_type": "rnabert", | |
| "normalization_type": "LayerNorm", | |
| "num_attention_heads": 32, | |
| "num_hidden_layers": 32, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "rope", | |
| "rotary_percent": 1.0, | |
| "seq_len_interpolation_factor": null, | |
| "tokenizer_type": "BertWordPieceLowerCase", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.38.0.dev0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 16 | |
| } | |