Upload model_config.json
Browse files- model_config.json +36 -0
model_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"attention_mode": "longformer",
|
| 3 |
+
"attention_probs_dropout_prob": 0.1,
|
| 4 |
+
"attention_window": [
|
| 5 |
+
512,
|
| 6 |
+
512,
|
| 7 |
+
512,
|
| 8 |
+
512,
|
| 9 |
+
512,
|
| 10 |
+
512,
|
| 11 |
+
512,
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512
|
| 17 |
+
],
|
| 18 |
+
"bos_token_id": 0,
|
| 19 |
+
"eos_token_id": 2,
|
| 20 |
+
"gradient_checkpointing": false,
|
| 21 |
+
"hidden_act": "gelu",
|
| 22 |
+
"hidden_dropout_prob": 0.1,
|
| 23 |
+
"hidden_size": 768,
|
| 24 |
+
"ignore_attention_mask": false,
|
| 25 |
+
"initializer_range": 0.02,
|
| 26 |
+
"intermediate_size": 3072,
|
| 27 |
+
"layer_norm_eps": 1e-05,
|
| 28 |
+
"max_position_embeddings": 4098,
|
| 29 |
+
"model_type": "longformer",
|
| 30 |
+
"num_attention_heads": 12,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"pad_token_id": 1,
|
| 33 |
+
"sep_token_id": 2,
|
| 34 |
+
"type_vocab_size": 1,
|
| 35 |
+
"vocab_size": 50265
|
| 36 |
+
}
|