danielhanchen commited on
Commit
adc7487
1 Parent(s): 378a080

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -17,7 +17,13 @@
17
  "rstrip": false,
18
  "single_word": false
19
  },
20
- "pad_token": "<unk>",
 
 
 
 
 
 
21
  "unk_token": {
22
  "content": "<unk>",
23
  "lstrip": false,
 
17
  "rstrip": false,
18
  "single_word": false
19
  },
20
+ "pad_token": {
21
+ "content": "<pad>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
  "unk_token": {
28
  "content": "<unk>",
29
  "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
@@ -60,9 +60,8 @@
60
  "clean_up_tokenization_spaces": false,
61
  "eos_token": "<eos>",
62
  "legacy": null,
63
- "model_max_length": 8192,
64
- "pad_token": "<unk>",
65
- "padding_side": "right",
66
  "sp_model_kwargs": {},
67
  "spaces_between_special_tokens": false,
68
  "tokenizer_class": "GemmaTokenizer",
 
60
  "clean_up_tokenization_spaces": false,
61
  "eos_token": "<eos>",
62
  "legacy": null,
63
+ "model_max_length": 1000000000000000019884624838656,
64
+ "pad_token": "<pad>",
 
65
  "sp_model_kwargs": {},
66
  "spaces_between_special_tokens": false,
67
  "tokenizer_class": "GemmaTokenizer",