|
{ |
|
"architectures": [ |
|
"BiGSForSequenceClassification" |
|
], |
|
"classifier_dropout": null, |
|
"decode": false, |
|
"finetuning_task": "mnli", |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 1024, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1", |
|
"2": "LABEL_2" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1, |
|
"LABEL_2": 2 |
|
}, |
|
"layer_norm_eps": 1e-12, |
|
"max_position_embeddings": 512, |
|
"model_type": "BiGS", |
|
"num_hidden_layers": 23, |
|
"num_ssm": 64, |
|
"pad_token_id": 0, |
|
"pooler_type": "non_padding_mean", |
|
"position_embedding_type": "absolute", |
|
"pre_norm": true, |
|
"transformers_version": "4.26.1", |
|
"type_vocab_size": 2, |
|
"use_auth_token": null, |
|
"use_cache": true, |
|
"vocab_size": 30522 |
|
} |
|
|