Commit
•
58f26a1
1
Parent(s):
2a9ade2
Upload LongformerForSequenceClassification
Browse files- config.json +40 -11
- pytorch_model.bin +2 -2
config.json
CHANGED
|
@@ -1,27 +1,56 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
|
|
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 1024,
|
|
|
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 4096,
|
| 14 |
-
"layer_norm_eps": 1e-
|
| 15 |
-
"max_position_embeddings":
|
| 16 |
-
"model_type": "
|
| 17 |
"num_attention_heads": 16,
|
| 18 |
"num_hidden_layers": 24,
|
| 19 |
-
"
|
| 20 |
-
"
|
| 21 |
"problem_type": "single_label_classification",
|
|
|
|
| 22 |
"torch_dtype": "float32",
|
| 23 |
"transformers_version": "4.34.0",
|
| 24 |
-
"type_vocab_size":
|
| 25 |
-
"
|
| 26 |
-
"vocab_size": 30522
|
| 27 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "allenai/longformer-large-4096",
|
| 3 |
"architectures": [
|
| 4 |
+
"LongformerForSequenceClassification"
|
| 5 |
],
|
| 6 |
+
"attention_mode": "longformer",
|
| 7 |
"attention_probs_dropout_prob": 0.1,
|
| 8 |
+
"attention_window": [
|
| 9 |
+
512,
|
| 10 |
+
512,
|
| 11 |
+
512,
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512,
|
| 16 |
+
512,
|
| 17 |
+
512,
|
| 18 |
+
512,
|
| 19 |
+
512,
|
| 20 |
+
512,
|
| 21 |
+
512,
|
| 22 |
+
512,
|
| 23 |
+
512,
|
| 24 |
+
512,
|
| 25 |
+
512,
|
| 26 |
+
512,
|
| 27 |
+
512,
|
| 28 |
+
512,
|
| 29 |
+
512,
|
| 30 |
+
512,
|
| 31 |
+
512,
|
| 32 |
+
512
|
| 33 |
+
],
|
| 34 |
+
"bos_token_id": 0,
|
| 35 |
+
"eos_token_id": 2,
|
| 36 |
"gradient_checkpointing": false,
|
| 37 |
"hidden_act": "gelu",
|
| 38 |
"hidden_dropout_prob": 0.1,
|
| 39 |
"hidden_size": 1024,
|
| 40 |
+
"ignore_attention_mask": false,
|
| 41 |
"initializer_range": 0.02,
|
| 42 |
"intermediate_size": 4096,
|
| 43 |
+
"layer_norm_eps": 1e-05,
|
| 44 |
+
"max_position_embeddings": 4098,
|
| 45 |
+
"model_type": "longformer",
|
| 46 |
"num_attention_heads": 16,
|
| 47 |
"num_hidden_layers": 24,
|
| 48 |
+
"onnx_export": false,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
"problem_type": "single_label_classification",
|
| 51 |
+
"sep_token_id": 2,
|
| 52 |
"torch_dtype": "float32",
|
| 53 |
"transformers_version": "4.34.0",
|
| 54 |
+
"type_vocab_size": 1,
|
| 55 |
+
"vocab_size": 50265
|
|
|
|
| 56 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaee5ca97a278707f7afe88ca4369c14b8bc5cd75a5a67127d0799ad47f86458
|
| 3 |
+
size 1738600369
|