|
{ |
|
"activation_dropout": 0.0, |
|
"architectures": [ |
|
"FunnelForSequenceClassification" |
|
], |
|
"attention_dropout": 0.1, |
|
"attention_type": "relative_shift", |
|
"block_repeats": [ |
|
1, |
|
1, |
|
1 |
|
], |
|
"block_sizes": [ |
|
4, |
|
4, |
|
4 |
|
], |
|
"d_head": 64, |
|
"d_inner": 3072, |
|
"d_model": 768, |
|
"hidden_act": "gelu_new", |
|
"hidden_dropout": 0.1, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1", |
|
"2": "LABEL_2", |
|
"3": "LABEL_3", |
|
"4": "LABEL_4", |
|
"5": "LABEL_5", |
|
"6": "LABEL_6", |
|
"7": "LABEL_7", |
|
"8": "LABEL_8", |
|
"9": "LABEL_9", |
|
"10": "LABEL_10", |
|
"11": "LABEL_11", |
|
"12": "LABEL_12", |
|
"13": "LABEL_13", |
|
"14": "LABEL_14", |
|
"15": "LABEL_15", |
|
"16": "LABEL_16", |
|
"17": "LABEL_17", |
|
"18": "LABEL_18", |
|
"19": "LABEL_19", |
|
"20": "LABEL_20", |
|
"21": "LABEL_21", |
|
"22": "LABEL_22", |
|
"23": "LABEL_23", |
|
"24": "LABEL_24", |
|
"25": "LABEL_25", |
|
"26": "LABEL_26" |
|
}, |
|
"initializer_range": 0.1, |
|
"initializer_std": null, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1, |
|
"LABEL_10": 10, |
|
"LABEL_11": 11, |
|
"LABEL_12": 12, |
|
"LABEL_13": 13, |
|
"LABEL_14": 14, |
|
"LABEL_15": 15, |
|
"LABEL_16": 16, |
|
"LABEL_17": 17, |
|
"LABEL_18": 18, |
|
"LABEL_19": 19, |
|
"LABEL_2": 2, |
|
"LABEL_20": 20, |
|
"LABEL_21": 21, |
|
"LABEL_22": 22, |
|
"LABEL_23": 23, |
|
"LABEL_24": 24, |
|
"LABEL_25": 25, |
|
"LABEL_26": 26, |
|
"LABEL_3": 3, |
|
"LABEL_4": 4, |
|
"LABEL_5": 5, |
|
"LABEL_6": 6, |
|
"LABEL_7": 7, |
|
"LABEL_8": 8, |
|
"LABEL_9": 9 |
|
}, |
|
"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", |
|
"rel_attn_type": "factorized", |
|
"separate_cls": true, |
|
"transformers_version": "4.3.2", |
|
"truncate_seq": true, |
|
"type_vocab_size": 3, |
|
"vocab_size": 30522 |
|
} |
|
|