|
{ |
|
"architectures": [ |
|
"LongformerModel" |
|
], |
|
"attention_probs_dropout_prob": 0.1, |
|
"attention_window": [ |
|
256, |
|
256, |
|
256, |
|
256, |
|
256, |
|
256, |
|
256, |
|
256, |
|
256, |
|
256, |
|
256, |
|
256 |
|
], |
|
"bos_token_id": 0, |
|
"classifier_dropout": null, |
|
"eos_token_id": 2, |
|
"hidden_act": "gelu", |
|
"hidden_dropout_prob": 0.1, |
|
"hidden_size": 768, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 3072, |
|
"layer_norm_eps": 1e-05, |
|
"max_position_embeddings": 16386, |
|
"model_type": "longformer", |
|
"num_attention_heads": 12, |
|
"num_hidden_layers": 12, |
|
"onnx_export": false, |
|
"pad_token_id": 1, |
|
"position_embedding_type": "absolute", |
|
"sep_token_id": 2, |
|
"transformers_version": "4.26.0", |
|
"type_vocab_size": 1, |
|
"vocab_size": 250002 |
|
} |
|
|