altkachenko11 commited on
Commit
cafffab
·
verified ·
1 Parent(s): f8f9aac

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +4 -28
  2. tokenizer.json +14 -2
  3. tokenizer_config.json +0 -7
special_tokens_map.json CHANGED
@@ -1,30 +1,6 @@
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
- "pad_token": {
17
- "content": "<|endoftext|>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "unk_token": {
24
- "content": "<|endoftext|>",
25
- "lstrip": false,
26
- "normalized": true,
27
- "rstrip": false,
28
- "single_word": false
29
- }
30
  }
 
1
  {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  }
tokenizer.json CHANGED
@@ -1,7 +1,19 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 50256,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 512,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": "BatchLongest",
11
+ "direction": "Right",
12
+ "pad_to_multiple_of": null,
13
+ "pad_id": 50256,
14
+ "pad_type_id": 0,
15
+ "pad_token": "<|endoftext|>"
16
+ },
17
  "added_tokens": [
18
  {
19
  "id": 50256,
tokenizer_config.json CHANGED
@@ -14,15 +14,8 @@
14
  "clean_up_tokenization_spaces": false,
15
  "eos_token": "<|endoftext|>",
16
  "extra_special_tokens": {},
17
- "max_length": 512,
18
  "model_max_length": 1024,
19
- "pad_to_multiple_of": null,
20
  "pad_token": "<|endoftext|>",
21
- "pad_token_type_id": 0,
22
- "padding_side": "right",
23
- "stride": 0,
24
  "tokenizer_class": "GPT2Tokenizer",
25
- "truncation_side": "right",
26
- "truncation_strategy": "longest_first",
27
  "unk_token": "<|endoftext|>"
28
  }
 
14
  "clean_up_tokenization_spaces": false,
15
  "eos_token": "<|endoftext|>",
16
  "extra_special_tokens": {},
 
17
  "model_max_length": 1024,
 
18
  "pad_token": "<|endoftext|>",
 
 
 
19
  "tokenizer_class": "GPT2Tokenizer",
 
 
20
  "unk_token": "<|endoftext|>"
21
  }