TinyPixel commited on
Commit
650831f
·
1 Parent(s): afc1f0a

Upload folder using huggingface_hub

Browse files
special_tokens_map.json CHANGED
@@ -13,6 +13,7 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "</s>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,7 +1,21 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 256,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": {
11
+ "Fixed": 256
12
+ },
13
+ "direction": "Left",
14
+ "pad_to_multiple_of": null,
15
+ "pad_id": 2,
16
+ "pad_type_id": 0,
17
+ "pad_token": "</s>"
18
+ },
19
  "added_tokens": [
20
  {
21
  "id": 0,
tokenizer_config.json CHANGED
@@ -30,7 +30,7 @@
30
  "clean_up_tokenization_spaces": false,
31
  "eos_token": "</s>",
32
  "model_max_length": 2048,
33
- "pad_token": null,
34
  "sp_model_kwargs": {},
35
  "tokenizer_class": "LlamaTokenizer",
36
  "unk_token": "<unk>",
 
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>",