Hugging Face's logo

Spaces:
OliverPerrin
/
LexiMind
Sleeping

App Files Community
OliverPerrin commited on
Commit
2d6b2fd
·
1 Parent(s): 1ca811e

Made necessary .json files available for hugging face hosting

Browse files
Files changed (8) hide show
  1. .gitignore +5 -1
  2. artifacts/hf_tokenizer/special_tokens_map.json +51 -0
  3. artifacts/hf_tokenizer/tokenizer.json +0 -0
  4. artifacts/hf_tokenizer/tokenizer_config.json +58 -0
  5. artifacts/hf_tokenizer/vocab.json +0 -0
  6. artifacts/labels.json +16 -0
  7. artifacts/tokenizer.json +0 -0
  8. checkpoints/.gitkeep +0 -0
.gitignore CHANGED
@@ -25,13 +25,17 @@ data/raw/
25
  data/processed/
26
  data/cache/
27
  *.csv
28
- *.json
29
  *.txt
30
  !requirements*.txt
31
 
32
  # Models
 
 
33
  *.pth
34
  *.ckpt
 
 
 
35
 
36
  # Logs
37
  logs/
 
25
  data/processed/
26
  data/cache/
27
  *.csv
 
28
  *.txt
29
  !requirements*.txt
30
 
31
  # Models
32
+ checkpoints/*.pt
33
+ !checkpoints/best.pt
34
  *.pth
35
  *.ckpt
36
+ *.json
37
+ !artifacts/*.json
38
+ !artifacts/hf_tokenizer/*.json
39
 
40
  # Logs
41
  logs/
artifacts/hf_tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
artifacts/hf_tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
artifacts/hf_tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 1000000000000000019884624838656,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "BartTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
artifacts/hf_tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
artifacts/labels.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "emotion": [
3
+ "anger",
4
+ "fear",
5
+ "joy",
6
+ "love",
7
+ "sadness",
8
+ "surprise"
9
+ ],
10
+ "topic": [
11
+ "Business",
12
+ "Sci/Tech",
13
+ "Sports",
14
+ "World"
15
+ ]
16
+ }
artifacts/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/.gitkeep ADDED
File without changes