{ "architectures": [ "RnaMsmForPreTraining" ], "attention_bias": true, "attention_dropout": 0.1, "attention_type": "standard", "bos_token_id": 1, "embed_positions_msa": true, "eos_token_id": 2, "head": { "act": null, "bias": true, "dropout": 0.0, "hidden_size": null, "layer_norm_eps": 1e-12, "num_labels": null, "output_name": null, "problem_type": null, "transform": null, "transform_act": "gelu" }, "hidden_act": "gelu", "hidden_dropout": 0.1, "hidden_size": 768, "id2label": { "0": "LABEL_0" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "LABEL_0": 0 }, "layer_norm_eps": 1e-12, "layer_type": "standard", "lm_head": { "act": null, "bias": true, "dropout": 0.0, "hidden_size": 768, "layer_norm_eps": 1e-12, "output_name": null, "transform": "nonlinear", "transform_act": "gelu" }, "mask_token_id": 4, "max_position_embeddings": 1024, "max_tokens_per_msa": 16384, "model_type": "rnamsm", "null_token_id": 5, "num_attention_heads": 12, "num_hidden_layers": 10, "pad_token_id": 0, "position_embedding_type": "absolute", "torch_dtype": "float32", "transformers_version": "4.41.2", "unk_token_id": 3, "use_cache": true, "vocab_size": 26 }