danielhanchen commited on
Commit
88d085b
1 Parent(s): de74cc4

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -13,7 +13,13 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<unk>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
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,
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6969e64047744a44bb3abfb5c50f8de0f7ed8b571d5444426ef931f651d1a0ef
3
- size 4241111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json CHANGED
@@ -39,9 +39,8 @@
39
  "clean_up_tokenization_spaces": false,
40
  "eos_token": "<eos>",
41
  "legacy": null,
42
- "model_max_length": 8192,
43
- "pad_token": "<unk>",
44
- "padding_side": "right",
45
  "sp_model_kwargs": {},
46
  "spaces_between_special_tokens": false,
47
  "tokenizer_class": "GemmaTokenizer",
 
39
  "clean_up_tokenization_spaces": false,
40
  "eos_token": "<eos>",
41
  "legacy": null,
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<pad>",
 
44
  "sp_model_kwargs": {},
45
  "spaces_between_special_tokens": false,
46
  "tokenizer_class": "GemmaTokenizer",