hjian42 commited on
Commit
d0b9ffe
1 Parent(s): 2a5668c

First model version

Browse files
added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<mask>": 64000}
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/bertweet-base",
3
+ "architectures": [
4
+ "RobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "B-LOC",
16
+ "1": "B-MISC",
17
+ "2": "B-ORG",
18
+ "3": "B-PER",
19
+ "4": "I-LOC",
20
+ "5": "I-MISC",
21
+ "6": "I-ORG",
22
+ "7": "I-PER",
23
+ "8": "O"
24
+ },
25
+ "initializer_range": 0.02,
26
+ "intermediate_size": 3072,
27
+ "label2id": {
28
+ "B-LOC": 0,
29
+ "B-MISC": 1,
30
+ "B-ORG": 2,
31
+ "B-PER": 3,
32
+ "I-LOC": 4,
33
+ "I-MISC": 5,
34
+ "I-ORG": 6,
35
+ "I-PER": 7,
36
+ "O": 8
37
+ },
38
+ "layer_norm_eps": 1e-05,
39
+ "max_position_embeddings": 130,
40
+ "model_type": "roberta",
41
+ "num_attention_heads": 12,
42
+ "num_hidden_layers": 12,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
45
+ "tokenizer_class": "BertweetTokenizer",
46
+ "torch_dtype": "float32",
47
+ "transformers_version": "4.12.5",
48
+ "type_vocab_size": 1,
49
+ "use_cache": true,
50
+ "vocab_size": 64001
51
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a62f19ad404ac8ebbbd8ab38dc61349457b0a433f2dcd59008c300bce675a8
3
+ size 537346801
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"normalization": false, "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 128, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "vinai/bertweet-base", "tokenizer_class": "BertweetTokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c1325e3b7f3b51e41a7a7f18d70f5316c548163e624dbc53267a38bb6aa378
3
+ size 2799
vocab.txt ADDED
The diff for this file is too large to render. See raw diff