vishwa27 commited on
Commit
ee31a48
1 Parent(s): fd33e95

Upload LongformerForSequenceClassification

Browse files
Files changed (2) hide show
  1. config.json +52 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/usr1/data/vishwavs/model_ckpts/model_ckpts/halueval_syn_pref_fb_model",
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
+ ],
22
+ "bos_token_id": 0,
23
+ "classifier_dropout": null,
24
+ "eos_token_id": 2,
25
+ "gradient_checkpointing": false,
26
+ "hidden_act": "gelu",
27
+ "hidden_dropout_prob": 0.1,
28
+ "hidden_size": 768,
29
+ "id2label": {
30
+ "0": "LABEL_0"
31
+ },
32
+ "ignore_attention_mask": false,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 3072,
35
+ "label2id": {
36
+ "LABEL_0": 0
37
+ },
38
+ "layer_norm_eps": 1e-05,
39
+ "max_position_embeddings": 4098,
40
+ "model_type": "longformer",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "onnx_export": false,
44
+ "pad_token_id": 1,
45
+ "position_embedding_type": "absolute",
46
+ "sep_token_id": 2,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.23.1",
49
+ "type_vocab_size": 1,
50
+ "use_cache": true,
51
+ "vocab_size": 50265
52
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6141ae26afacf4fc89be1fbb92c59fff8b1299b38a858fa583d1684f3c108f3b
3
+ size 594732369