HugoVoxx commited on
Commit
50ecf9d
1 Parent(s): a48e65c

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -17,13 +17,7 @@
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,
 
17
  "rstrip": false,
18
  "single_word": false
19
  },
20
+ "pad_token": "<eos>",
 
 
 
 
 
 
21
  "unk_token": {
22
  "content": "<unk>",
23
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6ce83119bb404f7f0a6e621b76759d476357dcd01241a90f9ca136ae2b3c11c
3
  size 34362972
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9afc4612a55c9c4b6223058eb59ae051813e1a51cb3f95b0f29ad864d50e4781
3
  size 34362972
tokenizer_config.json CHANGED
@@ -2004,7 +2004,7 @@
2004
  "clean_up_tokenization_spaces": false,
2005
  "eos_token": "<eos>",
2006
  "model_max_length": 1000000000000000019884624838656,
2007
- "pad_token": "<pad>",
2008
  "sp_model_kwargs": {},
2009
  "spaces_between_special_tokens": false,
2010
  "tokenizer_class": "GemmaTokenizer",
 
2004
  "clean_up_tokenization_spaces": false,
2005
  "eos_token": "<eos>",
2006
  "model_max_length": 1000000000000000019884624838656,
2007
+ "pad_token": "<eos>",
2008
  "sp_model_kwargs": {},
2009
  "spaces_between_special_tokens": false,
2010
  "tokenizer_class": "GemmaTokenizer",