TinyPixel commited on
Commit
983ae64
·
1 Parent(s): afc73ee

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +3 -4
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +11 -27
  5. vocab.json +0 -0
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,21 +1,20 @@
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": "</s>",
17
  "unk_token": {
18
- "content": "<unk>",
19
  "lstrip": false,
20
  "normalized": true,
21
  "rstrip": false,
 
1
  {
2
  "bos_token": {
3
+ "content": "<|endoftext|>",
4
  "lstrip": false,
5
  "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|endoftext|>",
11
  "lstrip": false,
12
  "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
16
  "unk_token": {
17
+ "content": "<|endoftext|>",
18
  "lstrip": false,
19
  "normalized": true,
20
  "rstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,23 +1,9 @@
1
  {
 
 
2
  "added_tokens_decoder": {
3
- "0": {
4
- "content": "<unk>",
5
- "lstrip": false,
6
- "normalized": true,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "1": {
12
- "content": "<s>",
13
- "lstrip": false,
14
- "normalized": true,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "2": {
20
- "content": "</s>",
21
  "lstrip": false,
22
  "normalized": true,
23
  "rstrip": false,
@@ -25,14 +11,12 @@
25
  "special": true
26
  }
27
  },
28
- "additional_special_tokens": [],
29
- "bos_token": "<s>",
30
- "clean_up_tokenization_spaces": false,
31
- "eos_token": "</s>",
32
  "model_max_length": 2048,
33
- "pad_token": "</s>",
34
- "sp_model_kwargs": {},
35
- "tokenizer_class": "LlamaTokenizer",
36
- "unk_token": "<unk>",
37
- "use_default_system_prompt": true
38
  }
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  "lstrip": false,
8
  "normalized": true,
9
  "rstrip": false,
 
11
  "special": true
12
  }
13
  },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
  "model_max_length": 2048,
19
+ "pad_token": null,
20
+ "tokenizer_class": "GPT2Tokenizer",
21
+ "unk_token": "<|endoftext|>"
 
 
22
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff