| { | |
| "architectures": [ | |
| "RiNALMoForPreTraining" | |
| ], | |
| "attention_dropout": 0.1, | |
| "bos_token_id": 1, | |
| "emb_layer_norm_before": true, | |
| "eos_token_id": 2, | |
| "head": null, | |
| "hidden_act": "gelu", | |
| "hidden_dropout": 0.1, | |
| "hidden_size": 480, | |
| "id2label": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 1920, | |
| "label2id": null, | |
| "layer_norm_eps": 1e-05, | |
| "learnable_beta": true, | |
| "lm_head": null, | |
| "mask_token_id": 4, | |
| "max_position_embeddings": 1024, | |
| "model_type": "rinalmo", | |
| "null_token_id": 5, | |
| "num_attention_heads": 20, | |
| "num_hidden_layers": 12, | |
| "num_labels": 1, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "rotary", | |
| "token_dropout": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.52.4", | |
| "unk_token_id": 3, | |
| "use_cache": true, | |
| "vocab_size": 26 | |
| } | |