Hugging Face's logo

danielhanchen
/
open_llama_3b

English
Model card Files
xet
 Community
danielhanchen commited on
Commit
0aef70e
·
1 Parent(s): cd65ff1

Upload tokenizer

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +30 -1
  2. tokenizer.json +0 -9
  3. tokenizer.model +1 -1
  4. tokenizer_config.json +40 -1
special_tokens_map.json CHANGED
@@ -1 +1,30 @@
1
- {"bos_token": {"content": "<s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "eos_token": {"content": "</s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "unk_token": {"content": "<unk>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json CHANGED
@@ -91,15 +91,6 @@
91
  }
92
  ],
93
  "special_tokens": {
94
- "</s>": {
95
- "id": "</s>",
96
- "ids": [
97
- 2
98
- ],
99
- "tokens": [
100
- "</s>"
101
- ]
102
- },
103
  "<s>": {
104
  "id": "<s>",
105
  "ids": [
 
91
  }
92
  ],
93
  "special_tokens": {
 
 
 
 
 
 
 
 
 
94
  "<s>": {
95
  "id": "<s>",
96
  "ids": [
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab1b681ec7fc02fed5edd3026687d7a692a918c4dd8e150ca2e3994a6229843b
3
  size 534194
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c4a3c9a9bbad64636d93660b6982940cec979a398f42684ba7194d118a3f21
3
  size 534194
tokenizer_config.json CHANGED
@@ -1 +1,40 @@
1
- {"add_bos_token": true, "add_eos_token": false, "model_max_length": 2048, "pad_token": null, "sp_model_kwargs": {}, "tokenizer_class": "LlamaTokenizer", "clean_up_tokenization_spaces": false, "bos_token": {"__type": "AddedToken", "content": "<s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "eos_token": {"__type": "AddedToken", "content": "</s>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}, "unk_token": {"__type": "AddedToken", "content": "<unk>", "lstrip": false, "normalized": true, "rstrip": false, "single_word": false}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "model_max_length": 2048,
22
+ "pad_token": {
23
+ "__type": "AddedToken",
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sp_model_kwargs": {},
31
+ "tokenizer_class": "LlamaTokenizer",
32
+ "unk_token": {
33
+ "__type": "AddedToken",
34
+ "content": "<unk>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }