vishwa27 commited on
Commit
17f4a15
1 Parent(s): 5b44e76

Upload LongformerForTokenClassification

Browse files
Files changed (2) hide show
  1. config.json +56 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/usr1/data/vishwavs/model_ckpts/model_ckpts/halueval_syn_all_fb_model_v2_2",
3
+ "architectures": [
4
+ "LongformerForTokenClassification"
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": "F-ERR",
31
+ "1": "Ignore",
32
+ "2": "O"
33
+ },
34
+ "ignore_attention_mask": false,
35
+ "initializer_range": 0.02,
36
+ "intermediate_size": 3072,
37
+ "label2id": {
38
+ "F-ERR": 0,
39
+ "Ignore": 1,
40
+ "O": 2
41
+ },
42
+ "layer_norm_eps": 1e-05,
43
+ "max_position_embeddings": 4098,
44
+ "model_type": "longformer",
45
+ "num_attention_heads": 12,
46
+ "num_hidden_layers": 12,
47
+ "onnx_export": false,
48
+ "pad_token_id": 1,
49
+ "position_embedding_type": "absolute",
50
+ "sep_token_id": 2,
51
+ "torch_dtype": "float32",
52
+ "transformers_version": "4.23.1",
53
+ "type_vocab_size": 1,
54
+ "use_cache": true,
55
+ "vocab_size": 50265
56
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:522653304c925aa1c659b7e1b0561082d6819b0195b9917a3696ea0e90603de7
3
+ size 592375561