Hugging Face's logo

MSey
/
tiny_BROLLLT_0001.1

Text Generation
Transformers
Safetensors
ger
llama
text-generation-inference
Inference Endpoints
Model card Files Community
MSey commited on
Commit
4e97143
•
1 Parent(s): b48e821

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +24 -24
  2. tokenizer.json +10 -6
  3. tokenizer_config.json +53 -41
special_tokens_map.json CHANGED
@@ -1,24 +1,24 @@
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": "[PAD]",
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": "[PAD]",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 591,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
@@ -34,6 +29,15 @@
34
  "rstrip": false,
35
  "normalized": false,
36
  "special": true
 
 
 
 
 
 
 
 
 
37
  }
38
  ],
39
  "normalizer": {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
29
  "rstrip": false,
30
  "normalized": false,
31
  "special": true
32
+ },
33
+ {
34
+ "id": 32000,
35
+ "content": "[PAD]",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
  }
42
  ],
43
  "normalizer": {
tokenizer_config.json CHANGED
@@ -1,41 +1,53 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false,
27
- "special": true
28
- }
29
- },
30
- "bos_token": "<s>",
31
- "clean_up_tokenization_spaces": false,
32
- "eos_token": "</s>",
33
- "legacy": false,
34
- "model_max_length": 1000000000000000019884624838656,
35
- "pad_token": "[PAD]",
36
- "padding_side": "right",
37
- "sp_model_kwargs": {},
38
- "tokenizer_class": "LlamaTokenizer",
39
- "unk_token": "<unk>",
40
- "use_default_system_prompt": false
41
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "32000": {
30
+ "content": "[PAD]",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<s>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "legacy": false,
42
+ "max_length": 591,
43
+ "model_max_length": 1000000000000000019884624838656,
44
+ "pad_token": "[PAD]",
45
+ "padding_side": "left",
46
+ "sp_model_kwargs": {},
47
+ "stride": 0,
48
+ "tokenizer_class": "LlamaTokenizer",
49
+ "truncation_side": "right",
50
+ "truncation_strategy": "longest_first",
51
+ "unk_token": "<unk>",
52
+ "use_default_system_prompt": false
53
+ }