| { | |
| "architectures": [ | |
| "BigBirdForPreTraining" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "attention_type": "block_sparse", | |
| "block_size": 64, | |
| "bos_token_id": 5, | |
| "classifier_dropout": null, | |
| "eos_token_id": 6, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu_new", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 4096, | |
| "model_type": "big_bird", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "num_random_blocks": 3, | |
| "pad_token_id": 0, | |
| "position_embedding_type": "absolute", | |
| "rescale_embeddings": false, | |
| "sep_token_id": 3, | |
| "tokenizer_class": "BertTokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.11.3", | |
| "type_vocab_size": 2, | |
| "use_bias": true, | |
| "use_cache": true, | |
| "vocab_size": 32500 | |
| } | |