Simran Khanuja commited on
Commit
df17349
1 Parent(s): f1d25d7

adding model files

Browse files
config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "embedding_size": 768,
6
+ "model_type": "bert",
7
+ "attention_probs_dropout_prob": 0.1,
8
+ "hidden_act": "gelu",
9
+ "hidden_dropout_prob": 0.1,
10
+ "hidden_size": 768,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 3072,
13
+ "max_position_embeddings": 512,
14
+ "num_attention_heads": 12,
15
+ "num_hidden_layers": 12,
16
+ "type_vocab_size": 2,
17
+ "vocab_size": 197285
18
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e65e3b7aaa3ce16d23fc4218783efd0417880655f8f398e6cb1a111a0de0c95f
3
+ size 953477430
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309c169a97534f335823e2be39fd85315f228012a68a4cefb5bc8f9c7dcd0aa0
3
+ size 1558943652
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "strip_accents": false, "lowercase": false, "do_lower_case": false}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff