crscardellino commited on
Commit
a3b3f91
2 Parent(s): 35f57d1 b51d7eb

Merge branch 'main' of https://huggingface.co/crscardellino/flisol-cba-martin-fierro

Browse files
Files changed (5) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +18 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +41 -0
  5. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
special_tokens_map.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|talk|>",
4
+ "<|ax1|>",
5
+ "<|ax2|>",
6
+ "<|ax3|>",
7
+ "<|ax4|>",
8
+ "<|ax5|>",
9
+ "<|ax6|>",
10
+ "<|ax7|>",
11
+ "<|ax8|>",
12
+ "<|ax9|>"
13
+ ],
14
+ "bos_token": "<|endoftext|>",
15
+ "eos_token": "<|endoftext|>",
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": "<|endoftext|>"
18
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "full_tokenizer_file": null,
23
+ "model_max_length": 1000000000000000019884624838656,
24
+ "pad_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
+ "tokenizer_class": "GPT2Tokenizer",
33
+ "unk_token": {
34
+ "__type": "AddedToken",
35
+ "content": "<|endoftext|>",
36
+ "lstrip": false,
37
+ "normalized": true,
38
+ "rstrip": false,
39
+ "single_word": false
40
+ }
41
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff