hhou435 commited on
Commit
284252e
1 Parent(s): eceeeed
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "albert",
3
+ "architectures": [
4
+ "AlbertForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "embedding_size": 128,
10
+ "eos_token_id": 3,
11
+ "hidden_act": "gelu_new",
12
+ "hidden_dropout_prob": 0,
13
+ "hidden_size": 768,
14
+ "initializer_range": 0.02,
15
+ "inner_group_num": 1,
16
+ "intermediate_size": 3072,
17
+ "layer_norm_eps": 1e-12,
18
+ "max_position_embeddings": 512,
19
+ "model_type": "albert",
20
+ "num_attention_heads": 12,
21
+ "num_hidden_groups": 1,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "type_vocab_size": 2,
25
+ "vocab_size": 21128
26
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58472840252d7729cc1d4de16c81d3ecb9010d7d139fa6b34926dc234a0116ae
3
+ size 40325143
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff