nreimers commited on
Commit
ad2780a
1 Parent(s): 402f9c0
README.md ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ #MiniLMv2
2
+ This is a MiniLMv2 model from: [https://github.com/microsoft/unilm](https://github.com/microsoft/unilm/tree/master/minilm)
config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForMaskedLM"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "initializer_range": 0.02,
10
+ "intermediate_size": 3072,
11
+ "layer_norm_eps": 1e-12,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "bert",
14
+ "num_attention_heads": 12,
15
+ "num_hidden_layers": 6,
16
+ "pad_token_id": 0,
17
+ "type_vocab_size": 2,
18
+ "vocab_size": 30522
19
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:903c70c23911388d3bc9bf87b0b470b059133de5e864d423575f66b3e5d99578
3
+ size 136353934
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.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff