JunxiongWang commited on
Commit
d06922d
1 Parent(s): 11be8d8

BiGS_128 MNLI checkpoint

Browse files

BiGS_128 trained in GLUE MNLI

config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BiGSForSequenceClassification"
4
+ ],
5
+ "classifier_dropout": null,
6
+ "decode": false,
7
+ "finetuning_task": "mnli",
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 1024,
11
+ "id2label": {
12
+ "0": "LABEL_0",
13
+ "1": "LABEL_1",
14
+ "2": "LABEL_2"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 3072,
18
+ "label2id": {
19
+ "LABEL_0": 0,
20
+ "LABEL_1": 1,
21
+ "LABEL_2": 2
22
+ },
23
+ "layer_norm_eps": 1e-12,
24
+ "max_position_embeddings": 128,
25
+ "model_type": "BiGS",
26
+ "num_hidden_layers": 23,
27
+ "num_ssm": 64,
28
+ "pad_token_id": 0,
29
+ "pooler_type": "non_padding_mean",
30
+ "position_embedding_type": "absolute",
31
+ "pre_norm": true,
32
+ "transformers_version": "4.26.1",
33
+ "type_vocab_size": 2,
34
+ "use_auth_token": null,
35
+ "use_cache": true,
36
+ "vocab_size": 30522
37
+ }
eval_results.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "eval_accuracy": 0.8634742740703005
3
+ }
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a348bf369807ae3cd74016b19f346924ec52200e5b6fdf70ff8e2b6a33d627e6
3
+ size 1385156750
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "do_lower_case": true,
4
+ "mask_token": "[MASK]",
5
+ "max_len": 128,
6
+ "model_max_length": 128,
7
+ "name_or_path": "JunxiongWang/BiGS_128",
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "special_tokens_map_file": null,
11
+ "strip_accents": null,
12
+ "tokenize_chinese_chars": true,
13
+ "tokenizer_class": "BertTokenizer",
14
+ "unk_token": "[UNK]"
15
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff