Hugging Face's logo

alfox
/
train_test_bloom560

Text Generation
Transformers
Safetensors
bloom
text-generation-inference
Model card Files
xet
 Community
cr0afm commited on
Commit
130e212
·
verified ·
1 Parent(s): 0d6291b

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +30 -24
  2. tokenizer.json +2 -2
  3. tokenizer_config.json +45 -47
special_tokens_map.json CHANGED
@@ -1,24 +1,30 @@
1
- {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": false,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "eos_token": {
10
- "content": "</s>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": "</s>",
17
- "unk_token": {
18
- "content": "<unk>",
19
- "lstrip": false,
20
- "normalized": false,
21
- "rstrip": false,
22
- "single_word": false
23
- }
24
- }
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d963066d6adae5034a1dc114c3ac444512de09928cf14ed4562ba94d9a440e66
3
- size 21763085
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15972849c91c78dfab27e2ef0eb53b17f95c4fe81be6664f7e85c6a7fffde0e
3
+ size 14500499
tokenizer_config.json CHANGED
@@ -1,47 +1,45 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<unk>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<s>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "</s>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<pad>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- }
36
- },
37
- "bos_token": "<s>",
38
- "clean_up_tokenization_spaces": false,
39
- "eos_token": "</s>",
40
- "merges_file": null,
41
- "model_max_length": 1000000000000000019884624838656,
42
- "pad_token": "</s>",
43
- "padding_side": "left",
44
- "tokenizer_class": "BloomTokenizer",
45
- "unk_token": "<unk>",
46
- "vocab_file": null
47
- }
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<s>",
38
+ "clean_up_tokenization_spaces": false,
39
+ "eos_token": "</s>",
40
+ "model_max_length": 1000000000000000019884624838656,
41
+ "pad_token": "<pad>",
42
+ "padding_side": "left",
43
+ "tokenizer_class": "BloomTokenizer",
44
+ "unk_token": "<unk>"
45
+ }