guntinik commited on
Commit
51a38ff
1 Parent(s): 910f6cb

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -13,13 +13,7 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": {
17
- "content": "<pad>",
18
- "lstrip": false,
19
- "normalized": false,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
  "unk_token": {
24
  "content": "<unk>",
25
  "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
@@ -1,14 +1,7 @@
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
- "padding": {
5
- "strategy": "BatchLongest",
6
- "direction": "Left",
7
- "pad_to_multiple_of": null,
8
- "pad_id": 32001,
9
- "pad_type_id": 0,
10
- "pad_token": "<pad>"
11
- },
12
  "added_tokens": [
13
  {
14
  "id": 0,
 
1
  {
2
  "version": "1.0",
3
  "truncation": null,
4
+ "padding": null,
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
tokenizer_config.json CHANGED
@@ -49,8 +49,8 @@
49
  "eos_token": "</s>",
50
  "legacy": false,
51
  "model_max_length": 1000000000000000019884624838656,
52
- "pad_token": "<pad>",
53
- "padding_side": "left",
54
  "processor_class": "LlavaProcessor",
55
  "sp_model_kwargs": {},
56
  "tokenizer_class": "LlamaTokenizer",
 
49
  "eos_token": "</s>",
50
  "legacy": false,
51
  "model_max_length": 1000000000000000019884624838656,
52
+ "pad_token": "</s>",
53
+ "padding_side": "right",
54
  "processor_class": "LlavaProcessor",
55
  "sp_model_kwargs": {},
56
  "tokenizer_class": "LlamaTokenizer",