xcjthu commited on
Commit
0f0b490
1 Parent(s): e12c6b2

upload the model

Browse files
.gitattributes CHANGED
@@ -14,3 +14,4 @@
14
  *.pb filter=lfs diff=lfs merge=lfs -text
15
  *.pt filter=lfs diff=lfs merge=lfs -text
16
  *.pth filter=lfs diff=lfs merge=lfs -text
 
14
  *.pb filter=lfs diff=lfs merge=lfs -text
15
  *.pt filter=lfs diff=lfs merge=lfs -text
16
  *.pth filter=lfs diff=lfs merge=lfs -text
17
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/xcj/LegalBert/LegalBert/PLMConfig/roberta-converted-lfm/",
3
+ "architectures": [
4
+ "LongformerForMaskedLM"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "attention_window": [
8
+ 512,
9
+ 512,
10
+ 512,
11
+ 512,
12
+ 512,
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "bos_token_id": 0,
22
+ "directionality": "bidi",
23
+ "eos_token_id": 2,
24
+ "gradient_checkpointing": false,
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "layer_norm_eps": 1e-12,
31
+ "max_position_embeddings": 4098,
32
+ "model_type": "longformer",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "output_past": true,
36
+ "pad_token_id": 1,
37
+ "pooler_fc_size": 768,
38
+ "pooler_num_attention_heads": 12,
39
+ "pooler_num_fc_layers": 3,
40
+ "pooler_size_per_head": 128,
41
+ "pooler_type": "first_token_transform",
42
+ "position_embedding_type": "absolute",
43
+ "sep_token_id": 2,
44
+ "transformers_version": "4.3.3",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 21128
48
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08d3551660a91f9c7a25f841538d47be08e8390ed937d52faf01aa0cc303afb4
3
+ size 505372506
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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": "/home/xiaochaojun/.cache/huggingface/transformers/d521373fc7ac35f63d56cf303de74a202403dcf1aaa792cd01f653694be59563.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "name_or_path": "hfl/chinese-roberta-wwm-ext"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff