Delete config.json
Browse files- config.json +0 -30
config.json
DELETED
|
@@ -1,30 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"BertForPreTraining"
|
| 4 |
-
],
|
| 5 |
-
"attention_probs_dropout_prob": 0.1,
|
| 6 |
-
"attention_window": 128,
|
| 7 |
-
"use_sparse_attention":true,
|
| 8 |
-
"directionality": "bidi",
|
| 9 |
-
"gradient_checkpointing": false,
|
| 10 |
-
"hidden_act": "gelu",
|
| 11 |
-
"hidden_dropout_prob": 0.1,
|
| 12 |
-
"hidden_size": 768,
|
| 13 |
-
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size": 3072,
|
| 15 |
-
"layer_norm_eps": 1e-12,
|
| 16 |
-
"max_position_embeddings": 4096,
|
| 17 |
-
"model_type": "longformer",
|
| 18 |
-
"num_attention_heads": 12,
|
| 19 |
-
"num_hidden_layers": 12,
|
| 20 |
-
"pad_token_id": 0,
|
| 21 |
-
"pooler_fc_size": 768,
|
| 22 |
-
"pooler_num_attention_heads": 12,
|
| 23 |
-
"pooler_num_fc_layers": 3,
|
| 24 |
-
"pooler_size_per_head": 128,
|
| 25 |
-
"pooler_type": "first_token_transform",
|
| 26 |
-
"type_vocab_size": 2,
|
| 27 |
-
"vocab_size": 21128
|
| 28 |
-
}
|
| 29 |
-
|
| 30 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|