kornwtp commited on
Commit
ad153eb
·
verified ·
1 Parent(s): 214282d

Initial commit

Browse files
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Tianduo/diffaug-sup-bert-base-uncased",
3
+ "alpha_1": 0.07,
4
+ "alpha_2": 0.007,
5
+ "architectures": [
6
+ "BertModel"
7
+ ],
8
+ "attention_probs_dropout_prob": 0.1,
9
+ "classifier_dropout": null,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_norm_eps": 1e-12,
17
+ "max_length": 64,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "bert",
20
+ "num_attention_heads": 12,
21
+ "num_experts": 2,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "position_embedding_type": "absolute",
25
+ "prefix_len": 16,
26
+ "top_routing": 1,
27
+ "torch_dtype": "float32",
28
+ "transformers_version": "4.30.2",
29
+ "type_vocab_size": 2,
30
+ "use_cache": true,
31
+ "vocab_size": 30522
32
+ }
fc_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d3e3e934ba238bf84a18316809265e522c745a00341d85ebaa836f457f1124a
3
+ size 7297
moe_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f241b8af00eff85a9f16a5b95811b57bbd6e9850ab300646b2ff03467d3b387d
3
+ size 94449746
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f866bcf2f52b58a2385647d7776e2f26ffcddf3b7f56e370b0a6a6a2455ccc0c
3
+ size 438003575
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 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "cls_token": "[CLS]",
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "pad_token": "[PAD]",
8
+ "sep_token": "[SEP]",
9
+ "strip_accents": null,
10
+ "tokenize_chinese_chars": true,
11
+ "tokenizer_class": "BertTokenizer",
12
+ "unk_token": "[UNK]"
13
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff