{ | |
"_name_or_path": "funnel-transformer/xlarge", | |
"activation_dropout": 0.0, | |
"architectures": [ | |
"FunnelForSequenceClassification" | |
], | |
"attention_dropout": 0.1, | |
"attention_type": "relative_shift", | |
"block_repeats": [ | |
1, | |
1, | |
1 | |
], | |
"block_sizes": [ | |
10, | |
10, | |
10 | |
], | |
"d_head": 64, | |
"d_inner": 4096, | |
"d_model": 1024, | |
"hidden_act": "gelu_new", | |
"hidden_dropout": 0.1, | |
"initializer_range": 0.1, | |
"initializer_std": null, | |
"layer_norm_eps": 1e-09, | |
"max_position_embeddings": 512, | |
"model_type": "funnel", | |
"n_head": 16, | |
"num_decoder_layers": 2, | |
"pool_q_only": true, | |
"pooling_type": "mean", | |
"problem_type": "single_label_classification", | |
"rel_attn_type": "factorized", | |
"separate_cls": true, | |
"torch_dtype": "float32", | |
"transformers_version": "4.20.1", | |
"truncate_seq": true, | |
"type_vocab_size": 3, | |
"vocab_size": 30522 | |
} | |