|
{ |
|
"activation_dropout": 0.0, |
|
"architectures": [ |
|
"FunnelBaseModel" |
|
], |
|
"attention_dropout": 0.1, |
|
"attention_type": "relative_shift", |
|
"block_sizes": [ |
|
4, |
|
4, |
|
4 |
|
], |
|
"d_head": 64, |
|
"d_inner": 3072, |
|
"d_model": 768, |
|
"hidden_act": "gelu_new", |
|
"hidden_dropout": 0.1, |
|
"initializer_range": 0.1, |
|
"layer_norm_eps": 1e-09, |
|
"max_position_embeddings": 512, |
|
"model_type": "funnel", |
|
"n_head": 12, |
|
"num_decoder_layers": 2, |
|
"pool_q_only": true, |
|
"pooling_type": "mean", |
|
"separate_cls": true, |
|
"truncate_seq": false, |
|
"type_vocab_size": 3, |
|
"vocab_size": 30522 |
|
} |
|
|