finiteautomata commited on
Commit
1e9980c
1 Parent(s): 4c1fe2a

Enhance training

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 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "vinai/bertweet-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 2,
9
+ "gradient_checkpointing": false,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "others",
15
+ "1": "joy",
16
+ "2": "sadness",
17
+ "3": "anger",
18
+ "4": "surprise",
19
+ "5": "disgust",
20
+ "6": "fear"
21
+ },
22
+ "initializer_range": 0.02,
23
+ "intermediate_size": 3072,
24
+ "label2id": {
25
+ "anger": 3,
26
+ "disgust": 5,
27
+ "fear": 6,
28
+ "joy": 1,
29
+ "others": 0,
30
+ "sadness": 2,
31
+ "surprise": 4
32
+ },
33
+ "layer_norm_eps": 1e-05,
34
+ "max_position_embeddings": 130,
35
+ "model_type": "roberta",
36
+ "num_attention_heads": 12,
37
+ "num_hidden_layers": 12,
38
+ "pad_token_id": 1,
39
+ "position_embedding_type": "absolute",
40
+ "tokenizer_class": "BertweetTokenizer",
41
+ "transformers_version": "4.6.1",
42
+ "type_vocab_size": 1,
43
+ "use_cache": true,
44
+ "vocab_size": 64001
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fba83ccf2c4d46545d59c0f9958abd7a2cfba4d5844340acc3808740d55e879
3
+ size 539707292
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"}
vocab.txt ADDED
The diff for this file is too large to render. See raw diff