mohammednuruddin commited on
Commit
58131cb
1 Parent(s): 396e73a

Upload tokenizer

Browse files
Files changed (2) hide show
  1. special_tokens_map.json +0 -1
  2. tokenizer_config.json +2 -2
special_tokens_map.json CHANGED
@@ -13,7 +13,6 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|im_end|>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "add_bos_token": true,
3
- "add_eos_token": true,
4
  "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
@@ -51,7 +51,7 @@
51
  "eos_token": "<|im_end|>",
52
  "legacy": true,
53
  "model_max_length": 1000000000000000019884624838656,
54
- "pad_token": "<|im_end|>",
55
  "sp_model_kwargs": {},
56
  "spaces_between_special_tokens": false,
57
  "tokenizer_class": "LlamaTokenizer",
 
1
  {
2
  "add_bos_token": true,
3
+ "add_eos_token": false,
4
  "add_prefix_space": true,
5
  "added_tokens_decoder": {
6
  "0": {
 
51
  "eos_token": "<|im_end|>",
52
  "legacy": true,
53
  "model_max_length": 1000000000000000019884624838656,
54
+ "pad_token": null,
55
  "sp_model_kwargs": {},
56
  "spaces_between_special_tokens": false,
57
  "tokenizer_class": "LlamaTokenizer",